This week’s parliamentary elections are widely seen as a referendum on both President Yoon Suk Yeol and his archrival, Lee Jae-myung, the opposition leader.

‘Gladiator Politics’ Dominate Election Season in Polarized South Korea

First minister calls for end to vexatious reports after far-right agitators attempt to ‘overwhelm’ official systems

Police spammed with complaints by neo-Nazis under new Scottish hate crime law | Hate crime | The Guardian

Hovering over a state visit to Washington is the possibility of a swing in American foreign policy if Donald Trump returns to the White House.

Japan and US Seek to Strengthen Ties as Kishida Visits - The New York Times

DURHAM, N.H. – Sophomores Macy Shultz (Adams, N.Y.) and Grace Lydon (Rowley, Mass.) each scored a career-high five points, as the UMass Lowell women&#x27;s lacrosse team (10-3, 1-2 AE) took down the New Hampshire Wildcats (2-9, 0-3 AE), 18-10, on Saturday afternoon at Tucker Field.

River Hawks Take Down New Hampshire, 18-10, For First Conference Win - UMass Lowell Athletics

Brian Dorsey, 52, is set to be executed on Tuesday for murdering his cousin and her husband in 2006.

Missouri death row inmate facing 'surgery without anesthesia': lawyer

PORTLAND, Maine (AP) — Power restoration efforts in Maine and New Hampshire entered another day on Saturday with more than 100,000 homes and businesses still in the dark several days after a storm brought powerful winds and heavy, wet snow.

Tens of Thousands Still Without Power Following Powerful Nor'easter in New England

Meteorologists now feel increasingly confident in models that show some parts of the country looking golden for the eclipse on Monday, April 8. Other parts of the country, though, may end up in a cloudy bust.

Eclipse cloud cover forecasts and maps show where skies will clear up for April 8's celestial show - CBS News

Actor Cole Brings Plenty, who had been missing since Sunday amid a domestic violence investigation, has been found dead, authorities in Kansas said Friday.

Missing '1923' actor Cole Brings Plenty, 27, found dead in Kansas

Relatives say the explosion was caused by a tree falling onto a propane tank.

Grandmother killed, girl injured in New Hampshire house explosion during snowstorm - CBS Boston

A nor’easter that dumped more than a foot of snow across the region, causing blackouts and flight cancellations, is expected to weaken on Friday, the National Weather Service said.

Thousands in Maine, New Hampshire and Vermont Without Power After Snowstorm - The New York Times

When you hear the phrase "humanoid robotics," you probably immediately imagine something akin to an audio-animatronic from a theme park or something out of The Terminator, and you wouldn't be entirely wrong. The traditional idea of a humanoid robot is driven by metal and gears functioning just beneath the surface to help create movement and an illusion of life. However, these kinds of humanoid robotics are outdated and rarely used in modern industries. The entire purpose of a humanoid robot is to be capable of performing human-like tasks. However, there is a growing need for a more nuanced and capable iteration of human robotics with the adaptability required for more complex interactions.​ Fortunately, Research Engineer Maciej Bakowicz is working on precisely that. In addition to being a Research Engineer, Bakowicz is also the Chief of Staff at Clone, a Polish humanoid robotics startup that is working to develop soft, musculoskeletal, and superintelligent androids, where he focuses on designing software controllers that integrate seamlessly with machine learning and AI systems to create more capable, accomplished, and sophisticated human robotics with full-blown neural control systems. Introducing Maciej Bakowicz Bakowicz began his career as a Working Student at Nokia during his last year of college. What started as a university collaboration project ended up with him becoming a part-time employee for two years while still in college and transitioning to a full-time role. At Nokia, Bakowicz focused mainly on end-client, internal use applications for BTS (Base Transceiver Station) statistics and configuration interfaces. After graduating, Bakowicz remained on the Nokia team for three more years as a Software Development Specialist before transitioning into a Technical Leader role. This was a more organizational position in which he supervised other engineers and architecture planners. He then took on his current role at Clone, where his technical expertise enabled him to lead his team in creating a naive teleoperation system for musculoskeletal androids that allowed for control without feedback.​ Bakowicz has developed a strong reputation for quickly delivering high-quality results without excessive revisions or follow-ups. He has been trusted to jump in and assist with many critical projects, especially when the team needs technical expertise to meet tight deadlines, and has consistently delivered exceptional results. Bakowicz's leadership now extends to overseeing international teams and mentoring junior engineers​, demonstrating how critical his role at Clone is to their innovative work. Challenges Faced Designing control systems that allow humanoid robots to move and interact as naturally as humans is complicated. For centuries, humankind has studied itself to garner further knowledge about its creation and how bodies function. This is knowledge that we still don't fully have, making replicating human functionality all the more difficult. But by incorporating real-time AI-driven decision-making into the process, Bakowicz and his team at Clone have made significant strides. Integrating electronics, low-level systems, and AI to achieve smooth, proportional robot movements​ has proved incredibly difficult, even without factoring in the development challenges and considerable resistance surrounding subjects like AI that Bakowicz has encountered.  With ethical considerations and AI still being a highly controversial subject, even in scientifically minded circles, Bakowicz and his team have seen even more obstacles between them and their success. The Solution to the Problem Bakowicz and his team are overcoming their development challenges by creating and implementing high-level controllers that integrate machine learning algorithms to ensure robots are more responsive and human-like. "We're developing human-like androids. I've been responsible for building the high-level software controller, and recently, we achieved a naive teleoperation system," Bakowicz explains. "This system allows users to control a robot hand using proportional muscle actuation without needing feedback from the robot, which has been crucial for showcasing the robot's capabilities to a wider audience." Bakowicz's role in the project has involved integrating the actuation controller, setting up Motion Capture glove integration, and writing the software that enables cross-platform operation. He also continuously improves the system's performance and stability, enhancing the robot's responsiveness and speed. Beyond being a ground-breaking technical achievement, this project exemplifies Bakowicz's vision of how robotics can be seamlessly integrated into day-to-day life and have the potential to play a crucial role in humanity's future. Practical Applications and Future Impact The success of this project has the potential to completely redefine human robotics as we know it. Thanks to the advanced control systems being developed by Bakowicz and his team at Clone, musculoskeletal androids of this kind could play an integral role in many important sectors, such as healthcare, home assistance, and other different industries. "As a Software Engineer and Chief of Staff, my role is to ensure the robot's performance, controllability, and smooth internal collaboration, laying the foundation for this technology to push the industry toward more human-like robotics," Bakowicz elaborates. "While it's a collective achievement, I'm proud to be part of this effort that has the potential to reshape the future of humanoid robots." Bakowicz's ultimate goal with the project extends far beyond simply creating functioning musculoskeletal androids. He hopes to develop noninvasive, functional, and aesthetically pleasing ​robots so that they stand the best chance of being embraced by the public and truly redefine the human experience. Call to Action for Developers "I want to contribute to the home robot movement, where robots become a natural and accepted part of the household—something people are proud to have, without being creepy or awkward. I envision robots that integrate seamlessly into daily life in a noninvasive way, much like smartphones or other standard technology. Ultimately, I aspire to continue to simplify human life by developing systems and technologies that improve human-robot interaction, making it as natural and unobtrusive as possible," Bakowicz concludes. As Bakowicz and his team at Clone continue to push forward into innovative and uncharted territory, he hopes their work will also encourage developers and engineers to explore AI integration in control systems, potentially inviting collaboration or open-source contributions. The future of humankind is changing, and Maciej Bakowicz's expertise and contributions at Clone will continue to play a pivotal role in creating advanced controllers that improve the adaptability and performance of human-like robots. When you hear the phrase "humanoid robotics," you probably immediately imagine something akin to an audio-animatronic from a theme park or something out of The Terminator , and you wouldn't be entirely wrong. The traditional idea of a humanoid robot is driven by metal and gears functioning just beneath the surface to help create movement and an illusion of life. The Terminator However, these kinds of humanoid robotics are outdated and rarely used in modern industries. The entire purpose of a humanoid robot is to be capable of performing human-like tasks. However, there is a growing need for a more nuanced and capable iteration of human robotics with the adaptability required for more complex interactions.​ Fortunately, Research Engineer Maciej Bakowicz is working on precisely that. In addition to being a Research Engineer, Bakowicz is also the Chief of Staff at Clone , a Polish humanoid robotics startup that is working to develop soft, musculoskeletal, and superintelligent androids, where he focuses on designing software controllers that integrate seamlessly with machine learning and AI systems to create more capable, accomplished, and sophisticated human robotics with full-blown neural control systems. Clone Clone Introducing Maciej Bakowicz Bakowicz began his career as a Working Student at Nokia during his last year of college. What started as a university collaboration project ended up with him becoming a part-time employee for two years while still in college and transitioning to a full-time role. At Nokia, Bakowicz focused mainly on end-client, internal use applications for BTS (Base Transceiver Station) statistics and configuration interfaces. After graduating, Bakowicz remained on the Nokia team for three more years as a Software Development Specialist before transitioning into a Technical Leader role. This was a more organizational position in which he supervised other engineers and architecture planners. He then took on his current role at Clone, where his technical expertise enabled him to lead his team in creating a naive teleoperation system for musculoskeletal androids that allowed for control without feedback.​ Bakowicz has developed a strong reputation for quickly delivering high-quality results without excessive revisions or follow-ups. He has been trusted to jump in and assist with many critical projects, especially when the team needs technical expertise to meet tight deadlines, and has consistently delivered exceptional results. Bakowicz's leadership now extends to overseeing international teams and mentoring junior engineers​, demonstrating how critical his role at Clone is to their innovative work. Challenges Faced Designing control systems that allow humanoid robots to move and interact as naturally as humans is complicated. For centuries, humankind has studied itself to garner further knowledge about its creation and how bodies function. This is knowledge that we still don't fully have, making replicating human functionality all the more difficult. But by incorporating real-time AI-driven decision-making into the process, Bakowicz and his team at Clone have made significant strides. Integrating electronics, low-level systems, and AI to achieve smooth, proportional robot movements​ has proved incredibly difficult, even without factoring in the development challenges and considerable resistance surrounding subjects like AI that Bakowicz has encountered.  With ethical considerations and AI still being a highly controversial subject, even in scientifically minded circles, Bakowicz and his team have seen even more obstacles between them and their success. The Solution to the Problem Bakowicz and his team are overcoming their development challenges by creating and implementing high-level controllers that integrate machine learning algorithms to ensure robots are more responsive and human-like. "We're developing human-like androids. I've been responsible for building the high-level software controller, and recently, we achieved a naive teleoperation system," Bakowicz explains. "This system allows users to control a robot hand using proportional muscle actuation without needing feedback from the robot, which has been crucial for showcasing the robot's capabilities to a wider audience." Bakowicz's role in the project has involved integrating the actuation controller, setting up Motion Capture glove integration, and writing the software that enables cross-platform operation. He also continuously improves the system's performance and stability, enhancing the robot's responsiveness and speed. Beyond being a ground-breaking technical achievement, this project exemplifies Bakowicz's vision of how robotics can be seamlessly integrated into day-to-day life and have the potential to play a crucial role in humanity's future. Practical Applications and Future Impact The success of this project has the potential to completely redefine human robotics as we know it. Thanks to the advanced control systems being developed by Bakowicz and his team at Clone, musculoskeletal androids of this kind could play an integral role in many important sectors, such as healthcare, home assistance, and other different industries. "As a Software Engineer and Chief of Staff, my role is to ensure the robot's performance, controllability, and smooth internal collaboration, laying the foundation for this technology to push the industry toward more human-like robotics," Bakowicz elaborates. "While it's a collective achievement, I'm proud to be part of this effort that has the potential to reshape the future of humanoid robots." Bakowicz's ultimate goal with the project extends far beyond simply creating functioning musculoskeletal androids. He hopes to develop noninvasive, functional, and aesthetically pleasing ​robots so that they stand the best chance of being embraced by the public and truly redefine the human experience. Call to Action for Developers "I want to contribute to the home robot movement, where robots become a natural and accepted part of the household—something people are proud to have, without being creepy or awkward. I envision robots that integrate seamlessly into daily life in a noninvasive way, much like smartphones or other standard technology. Ultimately, I aspire to continue to simplify human life by developing systems and technologies that improve human-robot interaction, making it as natural and unobtrusive as possible," Bakowicz concludes. As Bakowicz and his team at Clone continue to push forward into innovative and uncharted territory, he hopes their work will also encourage developers and engineers to explore AI integration in control systems, potentially inviting collaboration or open-source contributions. The future of humankind is changing, and Maciej Bakowicz's expertise and contributions at Clone will continue to play a pivotal role in creating advanced controllers that improve the adaptability and performance of human-like robots.

Training Musculoskeletal Androids With Neural Control Systems" By Maciej Bakowicz

Обучение на мускулно-скелетни андроиди с невронни контролни системи“ от Maciej Bakowicz

Entrenant Androides musculoesquelètics amb sistemes de control neuronal" de Maciej Bakowicz

"Entrenamiento de androides musculoesqueléticos con sistemas de control neuronal" Por Maciej Bakowicz

Entraînement des androïdes musculo-squelettiques avec des systèmes de contrôle neuronal" par Maciej Bakowicz

Մկանային-կմախքային անդրոիդների ուսուցում նյարդային կառավարման համակարգերով» Մացեյ Բակովիչի կողմից

「神経制御システムによる筋骨格アンドロイドのトレーニング」Maciej Bakowicz著

Formation ya ba Androids Musculosquelettiques Na Ba Systèmes Ya Contrôle Neural" Par Maciej Bakowicz

Мэдрэлийн хяналтын систем бүхий булчингийн булчингийн андройдуудыг сургах нь" Maciej Bakowicz

«Тренировка скелетно-мышечных андроидов с помощью систем нейронного управления» Мацей Бакович

Trajnimi i Android-ve muskuloskeletorë me sisteme të kontrollit nervor" Nga Maciej Bakowicz

عصبی کنٹرول سسٹم کے ساتھ Musculoskeletal Androids کی تربیت" بذریعہ Maciej Bakowicz

Ukuqeqesha i-Musculoskeletal Androids Nge-Neural Control Systems" Ngu-Maciej Bakowicz

**ZUG, Switzerland, December 17th, 2024/Chainwire/--**Atom Accelerator(AADAO), a governance-mandated DAO of the Cosmos Hub, has announced $250,000 funding support to Confio for the continued development and maintenance of CosmWasm throughout 2025. This funding is being matched by Neutron, the integrated application network in Cosmos, with a further $250,000. CosmWasm, developed by Confio since 2020, powers smart contract functionality for nearly 100 chains, enabling developers to create decentralized applications (dApps) that operate seamlessly across the interchain. In the past 12 months, contracts built with CosmWasm in the Cosmos ecosystem generated over $5.7 million in fees. Despite its widespread adoption, the Interchain Foundation has thus far been the primary funder for the development and maintenance of Cosmwasm. Following organizational restructuring at the Interchain Foundation (ICF), Confio’s funding for the year 2025 has been drastically reduced. “CosmWasm is a critical resource for the Cosmos ecosystem, underpinning many of the applications and chains that drive value to the interchain,” said AADAO contributors. “This proposal represents a collaborative effort to ensure its longevity and continued impact.” The contributions form the foundation of the CosmWasm Coalition initiative aimed at raising the approximately $2 million required to maintain and develop CosmWasm in 2025. The funds will enable Confio’s team to continue delivering on critical functions, including security research and incident response, feature development and performance optimization, documentation and developer support, SDK compatibility maintenance, and testing and developer experience (DevX) tooling improvements. This initiative builds on the Cosmos Hub’s previous support for CosmWasm, including the successful allocation of $1.25 million under Proposal #103 in March 2023. The Cosmos Hub relies on CosmWasm for permissioned smart contract capabilities, making its continued maintenance essential to the Hub’s operations and future upgrades. Many consumer chains utilizing the Hub’s Interchain Security have built their infrastructure on CosmWasm, making the framework vital to sustaining and expanding the ecosystem. By committing to early funding, the Cosmos Hub secures priority consideration for its technical needs and those of its consumer chains in Confio’s development roadmap. By taking the first step in committing funding, AADAO and Neutron hope that their initiative will encourage additional contributions from other ecosystem stakeholders, ensuring the financial stability of CosmWasm and the broader interchain ecosystem. About Atom Accelerator DAO (AADAO) Atom Accelerator DAO (AADAO) is a governance-mandated DAO of the Cosmos Hub. They have been formed and mandated to drive value for the Cosmos Hub & ATOM, supporting initiatives that either directly create economic impact or produce value that can drive its growth. From this, their current primary mandates are public grants & venture grants. Atom Accelerator’s venture arm strategically invests in promising early-stage web3 founders and startups both within and outside of the Cosmos Hub’s ecosystem. As experts within the Cosmos ecosystem, Atom Accelerator offers expertise, guidance, and support while driving value toward ATOM. Website Contact Marketing & Comms Lead Mr. T Atom Accelerator DAO press@atomaccelerator.com This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here **ZUG, Switzerland, December 17th, 2024/Chainwire/--**Atom Accelerator(AADAO), a governance-mandated DAO of the Cosmos Hub, has announced $250,000 funding support to Confio for the continued development and maintenance of CosmWasm throughout 2025. This funding is being matched by Neutron, the integrated application network in Cosmos, with a further $250,000. CosmWasm, developed by Confio since 2020, powers smart contract functionality for nearly 100 chains, enabling developers to create decentralized applications (dApps) that operate seamlessly across the interchain. In the past 12 months, contracts built with CosmWasm in the Cosmos ecosystem generated over $5.7 million in fees. Despite its widespread adoption, the Interchain Foundation has thus far been the primary funder for the development and maintenance of Cosmwasm. Following organizational restructuring at the Interchain Foundation (ICF), Confio’s funding for the year 2025 has been drastically reduced. “CosmWasm is a critical resource for the Cosmos ecosystem, underpinning many of the applications and chains that drive value to the interchain,” said AADAO contributors. “This proposal represents a collaborative effort to ensure its longevity and continued impact.” “CosmWasm is a critical resource for the Cosmos ecosystem, underpinning many of the applications and chains that drive value to the interchain,” said AADAO contributors. “This proposal represents a collaborative effort to ensure its longevity and continued impact.” The contributions form the foundation of the CosmWasm Coalition initiative aimed at raising the approximately $2 million required to maintain and develop CosmWasm in 2025. The funds will enable Confio’s team to continue delivering on critical functions, including security research and incident response, feature development and performance optimization, documentation and developer support, SDK compatibility maintenance, and testing and developer experience (DevX) tooling improvements. This initiative builds on the Cosmos Hub’s previous support for CosmWasm, including the successful allocation of $1.25 million under Proposal #103 in March 2023. The Cosmos Hub relies on CosmWasm for permissioned smart contract capabilities, making its continued maintenance essential to the Hub’s operations and future upgrades. Many consumer chains utilizing the Hub’s Interchain Security have built their infrastructure on CosmWasm, making the framework vital to sustaining and expanding the ecosystem. By committing to early funding, the Cosmos Hub secures priority consideration for its technical needs and those of its consumer chains in Confio’s development roadmap. By taking the first step in committing funding, AADAO and Neutron hope that their initiative will encourage additional contributions from other ecosystem stakeholders, ensuring the financial stability of CosmWasm and the broader interchain ecosystem. About Atom Accelerator DAO (AADAO) Atom Accelerator DAO (AADAO) is a governance-mandated DAO of the Cosmos Hub. They have been formed and mandated to drive value for the Cosmos Hub & ATOM, supporting initiatives that either directly create economic impact or produce value that can drive its growth. From this, their current primary mandates are public grants & venture grants. Atom Accelerator’s venture arm strategically invests in promising early-stage web3 founders and startups both within and outside of the Cosmos Hub’s ecosystem. As experts within the Cosmos ecosystem, Atom Accelerator offers expertise, guidance, and support while driving value toward ATOM. Website Website Website Contact Marketing & Comms Lead Mr. T Atom Accelerator DAO press@atomaccelerator.com This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here here here

Atom Accelerator Puts Weight Behind CosmWasm Coalition, Offers Matching Funding With Neutron

Atom Accelerator stavlja težinu iza koalicije CosmWasm, nudi finansiranje u skladu sa Neutronom

Atom Accelerator lægger vægt bag CosmWasm Coalition, tilbyder matchende finansiering med neutron

Ο επιταχυντής Atom βάζει βάρος πίσω από το CosmWasm Coalition, προσφέρει αντίστοιχη χρηματοδότηση με νετρόνιο

Atom Accelerator respalda la coalición CosmWasm y ofrece financiación equivalente a la de Neutron

Atom Azeleragailuak pisua jartzen du CosmWasm koalizioaren atzean, eta Neutroiarekin pareko finantzaketa eskaintzen du

L'accélérateur Atom soutient la coalition CosmWasm et propose un financement de contrepartie avec Neutron

O Atom Accelerator pon peso detrás da Coalición CosmWasm e ofrece financiamento equivalente con Neutron

מאיץ האטום שם משקל מאחורי קואליציית CosmWasm, מציע מימון תואם עם ניוטרון

Atom AcceleratorがCosmWasm連合を支援し、Neutronにマッチング資金を提供

Atom Accelerator coloca peso por trás da Coalizão CosmWasm e oferece financiamento correspondente com Neutron

அணு முடுக்கி CosmWasm கூட்டணிக்கு பின்னால் எடை போடுகிறது, நியூட்ரானுடன் பொருந்தக்கூடிய நிதியை வழங்குகிறது

Inilalagay ng Atom Accelerator ang Timbang sa Likod ng CosmWasm Coalition, Nag-aalok ng Pagtutugma ng Pagpopondo Sa Neutron

Table of Links Abstract and 1 Introduction 2 Related Work 2.1 Neural Codec Language Models and 2.2 Non-autoregressive Models 2.3 Diffusion Models and 2.4 Zero-shot Voice Cloning 3 Hierspeech++ and 3.1 Speech Representations 3.2 Hierarchical Speech Synthesizer 3.3 Text-to-Vec 3.4 Speech Super-resolution 3.5 Model Architecture 4 Speech Synthesis Tasks 4.1 Voice Conversion and 4.2 Text-to-Speech 4.3 Style Prompt Replication 5 Experiment and Result, and Dataset 5.2 Preprocessing and 5.3 Training 5.4 Evaluation Metrics 5.5 Ablation Study 5.6 Zero-shot Voice Conversion 5.7 High-diversity but High-fidelity Speech Synthesis 5.8 Zero-shot Text-to-Speech 5.9 Zero-shot Text-to-Speech with 1s Prompt 5.10 Speech Super-resolution 5.11 Additional Experiments with Other Baselines 6 Limitation and Quick Fix 7 Conclusion, Acknowledgement and References 2 RELATED WORK 2.1 Neural Codec Language Models Conventional sequence-to-sequence auto-regressive TTS models, such as Tacotron [79], have successfully paved the way for speech synthesis technologies. TransformerTTS [53] first adopted a Transformer network for TTS, and VTN [28] also utilizes a Transformer network for VC. However, these auto-regressive models suffer from a slow inference speed, in addition to a lack of robustness owing to challenges in aligning text and acoustic representations and the difficulty in predicting a continuous acoustic representation. Recently, neural audio codec model [16], [89] have replaced conventional acoustic representations with a high-compressed audio codec, which can reproduce the original waveform audio. Vall-E [78] was the first neural codec language model for speech synthesis utilizing a discrete audio unit and language models. By scaling up the dataset to 60,000 h, Vall-E could perform in-context learning using a neural audio codec. However, it possessed the same limitations as auto-regressive TTS models, such as a slow inference speed and a lack of robustness. Furthermore they have a high-dependency of their pre-trained neural audio codec, resulting in lowquality audio. To overcome this limitation, high-quality neural audio codec models, such as HiFi-Codec [85] and DAC [41], have been investigated. Furthermore, SPEARTTS [31] and Make-A-Voice [23] introduced a hierarchical speech synthesis framework from semantic to acoustic token to reduce the gap between text and speech. Moreover, to reduce inference speed and improve the robustness of autoregressive methods, SoundStorm [6] proposed parallel audio generation methods that generate the token of a neural audio codec. UniAudio [86] presented a multi-scale Transformer architecture to reduce the computational complexity of long audio sequences. 2.2 Non-autoregressive Models For fast and robust speech synthesis, FastSpeech [68] introduced a duration predictor to synthesize speech in parallel, and they significantly improved the robustness of speech synthesis by addressing the limitations of auto-regressive models such as repeating and skipping. To reduce the oneto-many mapping problem in non-autoregressive speech synthesis, FastSpeech 2 [67] adopted a variance adaptor that can reflect pitch and energy information. However, these models require an external duration extractor to align the text and speech. Glow-TTS [34] introduces a monotonic alignment search and normalizing flow to learn text-speech alignment and train the TTS model simultaneously. They add a blank token interspersed between phoneme tokens to increase robustness. VITS [35] combined the TTS model and a neural vocoder using VAE for end-to-end TTS frameworks with the aim of improving the quality of synthetic speech. NaturalSpeech [75] achieved human-level quality in a single speaker TTS by introducing a bidirectional normalizing flow and adopting a differentiable duration modeling and phoneme pre-training. Moreover, HierSpeech [48] leveraged a self-supervised speech representation in end-to-end speech synthesis, which significantly reduced the information gap between text and speech, thus addressing speech mispronunciations. In addition, HierVST [45] utilized a hierarchical VAE for zero-shot voice style transfer, and which significantly improved the voice style transfer performance in end-to-end speech synthesis models without any labels. ZS-TTS [37], WavthruVec [71] and VQTTS [17] utilized a self-supervised speech representation as an intermediate acoustic representation for robust speech synthesis. NANSY++ [9] introduced a unified speech synthesizer for various voice applications such as TTS, VC, singing voice synthesis, and voice control. Some studies [26] have combined a parallel TTS with LLMbased prosody modeling for expressive speech synthesis. This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license. Authors:
(1) Sang-Hoon Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea;
(2) Ha-Yeong Choi, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea;
(3) Seung-Bin Kim, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea;
(4) Seong-Whan Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea and a Corresponding author. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Related Work 2.1 Neural Codec Language Models and 2.2 Non-autoregressive Models 2.1 Neural Codec Language Models and 2.2 Non-autoregressive Models 2.3 Diffusion Models and 2.4 Zero-shot Voice Cloning 2.3 Diffusion Models and 2.4 Zero-shot Voice Cloning 3 Hierspeech++ and 3.1 Speech Representations 3 Hierspeech++ and 3.1 Speech Representations 3.2 Hierarchical Speech Synthesizer 3.2 Hierarchical Speech Synthesizer 3.3 Text-to-Vec 3.3 Text-to-Vec 3.4 Speech Super-resolution 3.4 Speech Super-resolution 3.5 Model Architecture 3.5 Model Architecture 4 Speech Synthesis Tasks 4.1 Voice Conversion and 4.2 Text-to-Speech 4.1 Voice Conversion and 4.2 Text-to-Speech 4.3 Style Prompt Replication 4.3 Style Prompt Replication 5 Experiment and Result, and Dataset 5 Experiment and Result, and Dataset 5.2 Preprocessing and 5.3 Training 5.2 Preprocessing and 5.3 Training 5.4 Evaluation Metrics 5.4 Evaluation Metrics 5.5 Ablation Study 5.5 Ablation Study 5.6 Zero-shot Voice Conversion 5.6 Zero-shot Voice Conversion 5.7 High-diversity but High-fidelity Speech Synthesis 5.7 High-diversity but High-fidelity Speech Synthesis 5.8 Zero-shot Text-to-Speech 5.8 Zero-shot Text-to-Speech 5.9 Zero-shot Text-to-Speech with 1s Prompt 5.9 Zero-shot Text-to-Speech with 1s Prompt 5.10 Speech Super-resolution 5.10 Speech Super-resolution 5.11 Additional Experiments with Other Baselines 5.11 Additional Experiments with Other Baselines 6 Limitation and Quick Fix 6 Limitation and Quick Fix 7 Conclusion, Acknowledgement and References 7 Conclusion, Acknowledgement and References 2 RELATED WORK 2.1 Neural Codec Language Models Conventional sequence-to-sequence auto-regressive TTS models, such as Tacotron [79], have successfully paved the way for speech synthesis technologies. TransformerTTS [53] first adopted a Transformer network for TTS, and VTN [28] also utilizes a Transformer network for VC. However, these auto-regressive models suffer from a slow inference speed, in addition to a lack of robustness owing to challenges in aligning text and acoustic representations and the difficulty in predicting a continuous acoustic representation. Recently, neural audio codec model [16], [89] have replaced conventional acoustic representations with a high-compressed audio codec, which can reproduce the original waveform audio. Vall-E [78] was the first neural codec language model for speech synthesis utilizing a discrete audio unit and language models. By scaling up the dataset to 60,000 h, Vall-E could perform in-context learning using a neural audio codec. However, it possessed the same limitations as auto-regressive TTS models, such as a slow inference speed and a lack of robustness. Furthermore they have a high-dependency of their pre-trained neural audio codec, resulting in lowquality audio. To overcome this limitation, high-quality neural audio codec models, such as HiFi-Codec [85] and DAC [41], have been investigated. Furthermore, SPEARTTS [31] and Make-A-Voice [23] introduced a hierarchical speech synthesis framework from semantic to acoustic token to reduce the gap between text and speech. Moreover, to reduce inference speed and improve the robustness of autoregressive methods, SoundStorm [6] proposed parallel audio generation methods that generate the token of a neural audio codec. UniAudio [86] presented a multi-scale Transformer architecture to reduce the computational complexity of long audio sequences. 2.2 Non-autoregressive Models For fast and robust speech synthesis, FastSpeech [68] introduced a duration predictor to synthesize speech in parallel, and they significantly improved the robustness of speech synthesis by addressing the limitations of auto-regressive models such as repeating and skipping. To reduce the oneto-many mapping problem in non-autoregressive speech synthesis, FastSpeech 2 [67] adopted a variance adaptor that can reflect pitch and energy information. However, these models require an external duration extractor to align the text and speech. Glow-TTS [34] introduces a monotonic alignment search and normalizing flow to learn text-speech alignment and train the TTS model simultaneously. They add a blank token interspersed between phoneme tokens to increase robustness. VITS [35] combined the TTS model and a neural vocoder using VAE for end-to-end TTS frameworks with the aim of improving the quality of synthetic speech. NaturalSpeech [75] achieved human-level quality in a single speaker TTS by introducing a bidirectional normalizing flow and adopting a differentiable duration modeling and phoneme pre-training. Moreover, HierSpeech [48] leveraged a self-supervised speech representation in end-to-end speech synthesis, which significantly reduced the information gap between text and speech, thus addressing speech mispronunciations. In addition, HierVST [45] utilized a hierarchical VAE for zero-shot voice style transfer, and which significantly improved the voice style transfer performance in end-to-end speech synthesis models without any labels. ZS-TTS [37], WavthruVec [71] and VQTTS [17] utilized a self-supervised speech representation as an intermediate acoustic representation for robust speech synthesis. NANSY++ [9] introduced a unified speech synthesizer for various voice applications such as TTS, VC, singing voice synthesis, and voice control. Some studies [26] have combined a parallel TTS with LLMbased prosody modeling for expressive speech synthesis. This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license. This paper is available on arxiv under CC BY-NC-SA 4.0 DEED license. available on arxiv Authors: (1) Sang-Hoon Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (2) Ha-Yeong Choi, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (3) Seung-Bin Kim, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (4) Seong-Whan Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea and a Corresponding author. Authors: Authors: (1) Sang-Hoon Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (2) Ha-Yeong Choi, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (3) Seung-Bin Kim, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea; (4) Seong-Whan Lee, Fellow, IEEE with the Department of Artificial Intelligence, Korea University, Seoul 02841, South Korea and a Corresponding author.

Neural Codec Language Models and Non-Autoregressive Models Explained

Neutrality, Trade-Offs, and the Future of Inflation Models

Table of Links Abstract and 1. Introduction Preliminaries


Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds


Experiments


Conclusion and References A. Notations B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition E. Node Classification F. Limitations of our work G. Some Related Definitions H. Computation of Canonical Representation I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 3 PROPOSED APPROACH 3.1 NOTATION 3.2 NEURAL NETWORKS ON SPD MANIFOLDS 3.2.1 FC LAYERS IN SPD NEURAL NETWORKS Our method for generalizing FC layers to the SPD manifold setting relies on a reformulation of SPD hypergyroplanes (Nguyen & Yang, 2023). We first recap the definition of SPD hypergyroplanes. Proof See Appendix I. In DNNs, an FC layer linearly transforms the input in such a way that the k-th dimension of the output corresponds to the signed distance from the output to the hyperplane that contains the origin and is orthonormal to the k-th axis of the output space. This interpretation has proven useful in generalizing FC layers to the hyperbolic setting (Shimizu et al., 2021). It remains to specify an orthonormal basis for each family of the considered Riemannian metrics of SPD manifolds. Proposition 3.4 gives such an orthonormal basis for AI gyrovector spaces along with the expression for the output of FC layers with Affine-Invariant metrics. Proof See Appendix J. Proof See Appendix K. Finally, we give the characterization of an orthonormal basis for LC gyrovector spaces and the expression for the output of FC layers with Log-Cholesky metrics. Proof See Appendix L. 3.2.2 CONVOLUTIONAL LAYERS IN SPD NEURAL NETWORKS In Chakraborty et al. (2020), the authors design a convolution operation for SPD neural networks. However, their method is based on the concept of weighted Frechet Mean, while ours is built upon ´ the concepts of SPD hypergyroplane and SPD pseudo-gyrodistance from an SPD matrix to an SPD hypergyroplane (Nguyen & Yang, 2023). Also, our convolution operation can be used for dimensionality reduction, while theirs always produces an output of the same dimension as the inputs. Authors:
(1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr);
(2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr);
(3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. Table of Links Abstract and 1. Introduction Abstract and 1. Introduction Preliminaries Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds Experiments Conclusion and References Preliminaries Preliminaries Preliminaries Proposed Approach 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds Proposed Approach 3.1 Notation 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds 3.4 Neural Networks on Grassmann Manifolds Experiments Experiments Experiments Conclusion and References Conclusion and References Conclusion and References A. Notations A. Notations B. MLR in Structure Spaces B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition D. Human Action Recognition E. Node Classification E. Node Classification F. Limitations of our work F. Limitations of our work G. Some Related Definitions G. Some Related Definitions H. Computation of Canonical Representation H. Computation of Canonical Representation I. Proof of Proposition 3.2 I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 N. Proof of Proposition 3.12 3 PROPOSED APPROACH 3.1 NOTATION 3.2 NEURAL NETWORKS ON SPD MANIFOLDS 3.2.1 FC LAYERS IN SPD NEURAL NETWORKS 3.2.1 FC LAYERS IN SPD NEURAL NETWORKS Our method for generalizing FC layers to the SPD manifold setting relies on a reformulation of SPD hypergyroplanes (Nguyen & Yang, 2023). We first recap the definition of SPD hypergyroplanes. Proof See Appendix I. Proof In DNNs, an FC layer linearly transforms the input in such a way that the k-th dimension of the output corresponds to the signed distance from the output to the hyperplane that contains the origin and is orthonormal to the k-th axis of the output space. This interpretation has proven useful in generalizing FC layers to the hyperbolic setting (Shimizu et al., 2021). It remains to specify an orthonormal basis for each family of the considered Riemannian metrics of SPD manifolds. Proposition 3.4 gives such an orthonormal basis for AI gyrovector spaces along with the expression for the output of FC layers with Affine-Invariant metrics. Proof See Appendix J. Proof Proof See Appendix K. Proof Finally, we give the characterization of an orthonormal basis for LC gyrovector spaces and the expression for the output of FC layers with Log-Cholesky metrics. Proof See Appendix L. Proof 3.2.2 CONVOLUTIONAL LAYERS IN SPD NEURAL NETWORKS 3.2.2 CONVOLUTIONAL LAYERS IN SPD NEURAL NETWORKS In Chakraborty et al. (2020), the authors design a convolution operation for SPD neural networks. However, their method is based on the concept of weighted Frechet Mean, while ours is built upon ´ the concepts of SPD hypergyroplane and SPD pseudo-gyrodistance from an SPD matrix to an SPD hypergyroplane (Nguyen & Yang, 2023). Also, our convolution operation can be used for dimensionality reduction, while theirs always produces an output of the same dimension as the inputs. Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). Authors: Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. available on arxiv available on arxiv

Reformulating Neural Layers on SPD Manifolds

Table of Links Abstract and 1. Introduction Preliminaries


Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds


Experiments


Conclusion and References A. Notations B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition E. Node Classification F. Limitations of our work G. Some Related Definitions H. Computation of Canonical Representation I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 2 PRELIMINARIES 2.1 SPD MANIFOLDS 2.2 GRASSMANN MANIFOLDS 2.3 NEURAL NETWORKS ON SPD AND GRASSMANN MANIFOLDS 2.3.1 NEURAL NETWORKS ON SPD MANIFOLDS The work in Huang & Gool (2017) introduces SPDNet with three novel layers, i.e., Bimap, LogEig, and ReEig layers that has become one of the most successful architectures in the field. In Brooks et al. (2019), the authors further improve SPDNet by developing Riemannian versions of batch normalization layers. Following these works, some works (Nguyen et al., 2019; Nguyen, 2021; Wang et al., 2021; Kobler et al., 2022; Ju & Guan, 2023) design variants of Bimap and batch normalization layers in SPD neural networks. The work in Chakraborty et al. (2020) presents a different approach based on intrinsic operations on SPD manifolds. Their proposed layers have nice theoretical properties. A common limitation of the above works is that they do not provide necessary mathematical tools for constructing many essential building blocks of DNNs on SPD manifolds. Recently, some works (Nguyen, 2022a;b; Nguyen & Yang, 2023) take a gyrovector space approach that enables natural generalizations of some building blocks of DNNs, e.g., MLR for SPD neural networks. 2.3.2 NEURAL NETWORKS ON GRASSMANN MANIFOLDS In Huang et al. (2018), the authors propose GrNet that explores the same rule of matrix backpropagation (Ionescu et al., 2015) as SPDNet. Some existing works (Wang & Wu, 2020; Souza et al.,2020) are also inspired by GrNet. Like their SPD counterparts, most existing Grassmann neural networks are not built upon a mathematical framework that allows one to generalize a broad class of DNNs to Grassmann manifolds. Using a gyrovector space approach, Nguyen & Yang (2023) has shown that some concepts in Euclidean spaces can be naturally extended to Grassmann manifolds. Authors:
(1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr);
(2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr);
(3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. Table of Links Abstract and 1. Introduction Abstract and 1. Introduction Preliminaries Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds Experiments Conclusion and References Preliminaries Preliminaries Preliminaries Proposed Approach 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds Proposed Approach 3.1 Notation 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds 3.4 Neural Networks on Grassmann Manifolds Experiments Experiments Experiments Conclusion and References Conclusion and References Conclusion and References A. Notations A. Notations B. MLR in Structure Spaces B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition D. Human Action Recognition E. Node Classification E. Node Classification F. Limitations of our work F. Limitations of our work G. Some Related Definitions G. Some Related Definitions H. Computation of Canonical Representation H. Computation of Canonical Representation I. Proof of Proposition 3.2 I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 N. Proof of Proposition 3.12 2 PRELIMINARIES 2.1 SPD MANIFOLDS 2.1 SPD MANIFOLDS 2.2 GRASSMANN MANIFOLDS 2.3 NEURAL NETWORKS ON SPD AND GRASSMANN MANIFOLDS 2.3.1 NEURAL NETWORKS ON SPD MANIFOLDS 2.3.1 NEURAL NETWORKS ON SPD MANIFOLDS The work in Huang & Gool (2017) introduces SPDNet with three novel layers, i.e., Bimap, LogEig, and ReEig layers that has become one of the most successful architectures in the field. In Brooks et al. (2019), the authors further improve SPDNet by developing Riemannian versions of batch normalization layers. Following these works, some works (Nguyen et al., 2019; Nguyen, 2021; Wang et al., 2021; Kobler et al., 2022; Ju & Guan, 2023) design variants of Bimap and batch normalization layers in SPD neural networks. The work in Chakraborty et al. (2020) presents a different approach based on intrinsic operations on SPD manifolds. Their proposed layers have nice theoretical properties. A common limitation of the above works is that they do not provide necessary mathematical tools for constructing many essential building blocks of DNNs on SPD manifolds. Recently, some works (Nguyen, 2022a;b; Nguyen & Yang, 2023) take a gyrovector space approach that enables natural generalizations of some building blocks of DNNs, e.g., MLR for SPD neural networks. 2.3.2 NEURAL NETWORKS ON GRASSMANN MANIFOLDS 2.3.2 NEURAL NETWORKS ON GRASSMANN MANIFOLDS In Huang et al. (2018), the authors propose GrNet that explores the same rule of matrix backpropagation (Ionescu et al., 2015) as SPDNet. Some existing works (Wang & Wu, 2020; Souza et al.,2020) are also inspired by GrNet. Like their SPD counterparts, most existing Grassmann neural networks are not built upon a mathematical framework that allows one to generalize a broad class of DNNs to Grassmann manifolds. Using a gyrovector space approach, Nguyen & Yang (2023) has shown that some concepts in Euclidean spaces can be naturally extended to Grassmann manifolds. Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). Authors: Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. available on arxiv available on arxiv

Researchers Unlock Advanced Building Blocks for Neural Networks on Matrix Manifolds

Authors:
(1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr);
(2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr);
(3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). Table of Links Abstract and 1. Introduction Preliminaries


Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds


Experiments


Conclusion and References A. Notations B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition E. Node Classification F. Limitations of our work G. Some Related Definitions H. Computation of Canonical Representation I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 ABSTRACT Deep neural networks (DNNs) on Riemannian manifolds have garnered increasing interest in various applied areas. For instance, DNNs on spherical and hyperbolic manifolds have been designed to solve a wide range of computer vision and nature language processing tasks. One of the key factors that contribute to the success of these networks is that spherical and hyperbolic manifolds have the rich algebraic structures of gyrogroups and gyrovector spaces. This enables principled and effective generalizations of the most successful DNNs to these manifolds. Recently, some works have shown that many concepts in the theory of gyrogroups and gyrovector spaces can also be generalized to matrix manifolds such as Symmetric Positive Definite (SPD) and Grassmann manifolds. As a result, some building blocks for SPD and Grassmann neural networks, e.g., isometric models and multinomial logistic regression (MLR) can be derived in a way that is fully analogous to their spherical and hyperbolic counterparts. Building upon these works, we design fully-connected (FC) and convolutional layers for SPD neural networks. We also develop MLR on Symmetric Positive Semi-definite (SPSD) manifolds, and propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective. We demonstrate the effectiveness of the proposed approach in the human action recognition and node classification tasks. 1 INTRODUCTION In recent years, deep neural networks on Riemannian manifolds have achieved impressive performance in many applications (Ganea et al., 2018; Skopek et al., 2020; Cruceru et al., 2021; Shimizu et al., 2021). The most popular neural networks in this family operate on hyperbolic spaces. Such spaces of constant sectional curvature, like spherical spaces, have the rich algebraic structure of gyrovector spaces. The theory of gyrovector spaces (Ungar, 2002; 2005; 2014) offers an elegant and powerful framework based on which natural generalizations (Ganea et al., 2018; Shimizu et al., 2021) of essential building blocks in DNNs are constructed for hyperbolic neural networks (HNNs). Matrix manifolds such as SPD and Grassmann manifolds offer a convenient trade-off between structural richness and computational tractability (Cruceru et al., 2021; Lopez et al., 2021). Therefore, in ´ many applications, neural networks on matrix manifolds are attractive alternatives to their hyperbolic counterparts. However, unlike the approaches in Ganea et al. (2018); Shimizu et al. (2021), most existing approaches for building SPD and Grassmann neural networks (Dong et al., 2017; Huang & Gool, 2017; Huang et al., 2018; Nguyen et al., 2019; Brooks et al., 2019; Nguyen, 2021; Wang et al., 2021) do not provide necessary techniques and mathematical tools to generalize a broad class of DNNs to the considered manifolds. Recently, the authors of Kim (2020); Nguyen (2022b) have shown that SPD and Grassmann manifolds have the structure of gyrovector spaces or that of nonreductive gyrovector spaces (Nguyen, 2022b) that share remarkable analogies with gyrovector spaces. The work in Nguyen & Yang (2023) takes one step forward in that direction by generalizing several notions in gyrovector spaces, e.g., the inner product and gyrodistance (Ungar, 2014) to SPD and Grassmann manifolds. This allows one to characterize certain gyroisometries of these manifolds and to construct MLR on SPD manifolds. Although some useful notions in gyrovector spaces have been generalized to SPD and Grassmann manifolds (Nguyen, 2022a;b; Nguyen & Yang, 2023) that set the stage for an effective way of building neural networks on these manifolds, many questions remain open. In this paper, we aim at addressing some limitations of existing works using a gyrovector space approach. Our contributions can be summarized as follows: We generalize FC and convolutional layers to the SPD manifold setting.


We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective (Bendokat et al., 2020) without resorting to any approximation schemes. We then show how to construct graph convolutional networks (GCNs) on Grassmann manifolds.


We develop MLR on SPSD manifolds.


We showcase our approach in the human action recognition and node classification tasks. This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). Authors: Authors: (1) Xuan Son Nguyen, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (xuan-son.nguyen@ensea.fr); (2) Shuo Yang, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (son.nguyen@ensea.fr); (3) Aymeric Histace, ETIS, UMR 8051, CY Cergy Paris University, ENSEA, CNRS, France (aymeric.histace@ensea.fr). Table of Links Abstract and 1. Introduction Abstract and 1. Introduction Preliminaries Proposed Approach
3.1 Notation
3.2 Nueral Networks on SPD Manifolds
3.3 MLR in Structure Spaces
3.4 Neural Networks on Grassmann Manifolds Experiments Conclusion and References Preliminaries Preliminaries Preliminaries Proposed Approach 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds Proposed Approach 3.1 Notation 3.1 Notation 3.2 Nueral Networks on SPD Manifolds 3.2 Nueral Networks on SPD Manifolds 3.3 MLR in Structure Spaces 3.3 MLR in Structure Spaces 3.4 Neural Networks on Grassmann Manifolds 3.4 Neural Networks on Grassmann Manifolds Experiments Experiments Experiments Conclusion and References Conclusion and References Conclusion and References A. Notations A. Notations B. MLR in Structure Spaces B. MLR in Structure Spaces C. Formulation of MLR from the Perspective of Distances to Hyperplanes C. Formulation of MLR from the Perspective of Distances to Hyperplanes D. Human Action Recognition D. Human Action Recognition E. Node Classification E. Node Classification F. Limitations of our work F. Limitations of our work G. Some Related Definitions G. Some Related Definitions H. Computation of Canonical Representation H. Computation of Canonical Representation I. Proof of Proposition 3.2 I. Proof of Proposition 3.2 J. Proof of Proposition 3.4 J. Proof of Proposition 3.4 K. Proof of Proposition 3.5 K. Proof of Proposition 3.5 L. Proof of Proposition 3.6 L. Proof of Proposition 3.6 M. Proof of Proposition 3.11 M. Proof of Proposition 3.11 N. Proof of Proposition 3.12 N. Proof of Proposition 3.12 ABSTRACT Deep neural networks (DNNs) on Riemannian manifolds have garnered increasing interest in various applied areas. For instance, DNNs on spherical and hyperbolic manifolds have been designed to solve a wide range of computer vision and nature language processing tasks. One of the key factors that contribute to the success of these networks is that spherical and hyperbolic manifolds have the rich algebraic structures of gyrogroups and gyrovector spaces. This enables principled and effective generalizations of the most successful DNNs to these manifolds. Recently, some works have shown that many concepts in the theory of gyrogroups and gyrovector spaces can also be generalized to matrix manifolds such as Symmetric Positive Definite (SPD) and Grassmann manifolds. As a result, some building blocks for SPD and Grassmann neural networks, e.g., isometric models and multinomial logistic regression (MLR) can be derived in a way that is fully analogous to their spherical and hyperbolic counterparts. Building upon these works, we design fully-connected (FC) and convolutional layers for SPD neural networks. We also develop MLR on Symmetric Positive Semi-definite (SPSD) manifolds, and propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective. We demonstrate the effectiveness of the proposed approach in the human action recognition and node classification tasks. 1 INTRODUCTION In recent years, deep neural networks on Riemannian manifolds have achieved impressive performance in many applications (Ganea et al., 2018; Skopek et al., 2020; Cruceru et al., 2021; Shimizu et al., 2021). The most popular neural networks in this family operate on hyperbolic spaces. Such spaces of constant sectional curvature, like spherical spaces, have the rich algebraic structure of gyrovector spaces. The theory of gyrovector spaces (Ungar, 2002; 2005; 2014) offers an elegant and powerful framework based on which natural generalizations (Ganea et al., 2018; Shimizu et al., 2021) of essential building blocks in DNNs are constructed for hyperbolic neural networks (HNNs). Matrix manifolds such as SPD and Grassmann manifolds offer a convenient trade-off between structural richness and computational tractability (Cruceru et al., 2021; Lopez et al., 2021). Therefore, in ´ many applications, neural networks on matrix manifolds are attractive alternatives to their hyperbolic counterparts. However, unlike the approaches in Ganea et al. (2018); Shimizu et al. (2021), most existing approaches for building SPD and Grassmann neural networks (Dong et al., 2017; Huang & Gool, 2017; Huang et al., 2018; Nguyen et al., 2019; Brooks et al., 2019; Nguyen, 2021; Wang et al., 2021) do not provide necessary techniques and mathematical tools to generalize a broad class of DNNs to the considered manifolds. Recently, the authors of Kim (2020); Nguyen (2022b) have shown that SPD and Grassmann manifolds have the structure of gyrovector spaces or that of nonreductive gyrovector spaces (Nguyen, 2022b) that share remarkable analogies with gyrovector spaces. The work in Nguyen & Yang (2023) takes one step forward in that direction by generalizing several notions in gyrovector spaces, e.g., the inner product and gyrodistance (Ungar, 2014) to SPD and Grassmann manifolds. This allows one to characterize certain gyroisometries of these manifolds and to construct MLR on SPD manifolds. Although some useful notions in gyrovector spaces have been generalized to SPD and Grassmann manifolds (Nguyen, 2022a;b; Nguyen & Yang, 2023) that set the stage for an effective way of building neural networks on these manifolds, many questions remain open. In this paper, we aim at addressing some limitations of existing works using a gyrovector space approach. Our contributions can be summarized as follows: We generalize FC and convolutional layers to the SPD manifold setting. We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective (Bendokat et al., 2020) without resorting to any approximation schemes. We then show how to construct graph convolutional networks (GCNs) on Grassmann manifolds. We develop MLR on SPSD manifolds. We showcase our approach in the human action recognition and node classification tasks. We generalize FC and convolutional layers to the SPD manifold setting. We generalize FC and convolutional layers to the SPD manifold setting. We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective (Bendokat et al., 2020) without resorting to any approximation schemes. We then show how to construct graph convolutional networks (GCNs) on Grassmann manifolds. We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective (Bendokat et al., 2020) without resorting to any approximation schemes. We then show how to construct graph convolutional networks (GCNs) on Grassmann manifolds. We develop MLR on SPSD manifolds. We develop MLR on SPSD manifolds. We showcase our approach in the human action recognition and node classification tasks. We showcase our approach in the human action recognition and node classification tasks. This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license. available on arxiv available on arxiv

Matrix Manifold Neural Networks

Authors:
(1) Limeng Zhang, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia;
(2) M. Ali Babar, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia. Table of Links Abstract and 1 Introduction 1.1 Configuration Parameter Tuning Challenges and 1.2 Contributions 2 Tuning Objectives 3 Overview of Tuning Framework 4 Workload Characterization and 4.1 Query-level Characterization 4.2 Runtime-based Characterization 5 Feature Pruning and 5.1 Workload-level Pruning 5.2 Configuration-level Pruning 5.3 Summary 6 Knowledge from Experience 7 Configuration Recommendation and 7.1 Bayesian Optimization 7.2 Neural Network 7.3 Reinforcement Learning 7.4 Search-based Solutions 8 Experimental Setting 9 Related Work 10 Discussion and Conclusion, and References 7.2 Neural Network Neural Network (NN)-based Solutions for automatic tuning leverage the power of artificial neural networks to model the complex relationships between configuration parameters and system performance, enabling efficient tuning without the need for exhaustive search or manual intervention. 7.2.1 NN-based solutions Tan et al. propose iBTune [15], individualized buffer tuning, to automatically reduce the buffer size for any individual database instance while still maintaining the quality of service for its response time. It leverages information from similar workloads to determine the tolerable miss ratio of each instance. Then, it utilizes the relationship between miss ratios and allocated memory sizes to individually optimize the target buffer pool sizes based on a large deviation analysis for the LRU caching model. To provide a guaranteed level of service level agreement (SLA), it designs a pairwise deep neural network (DNN) that predicts the upper bounds of the request response time by learning features from measurements on pairs of instances. Specifically, in the training phase, the NN network takes input of the performance metrics (logical reads, I/O reads, queries per second (QPS), CPU usage, miss ratio) of the target database instance and a similar database instance, the response time (RT) of the similar instance, and the encoding of the current time. The output of the network is the RT. In the testing phase, the previously observed sample of the target is selected as the similar instance. If the predicted RT meets the requirement, the computed new buffer pool size is sent for execution. Authors in [14] proposed Ottertune-DNN by adopting the OtterTune framework [8] and replacing its gaussian process model with a neural network model. Same to Ottertune [8], the raw data for each previous workload is collected and compared with the target workload. Data from the most similar previous workload are then merged with the target workload data to train a neural network model, which replaces the GP model in the original OtterTune. Finally, the algorithm recommends the next configuration to run by optimizing the model. The neural network model is a stacked 2-layer neural network with 64 neurons connected using ReLU as the activation function, and there is one dropout layer among the two hidden layers. Additionally, Gaussian noise is added to the neural network parameters to control the trade-off between exploration and exploitation, with increased exploitation throughout the tuning session achieved by reducing the scale of the noise. LITE [21] achieves configuration tuning for Spark applications by leveraging the power of NN to analyze the application code semantics as well as scheduling information during its execution. Its framework consists of an offline training phase to estimate the performance of a Spark application for a given knob configuration, and an online recommendation phase to recommend appropriate knobs for a given Spark application. In the offline training phase, LITE proposes a code learning framework, Neural Estimator via Code and Scheduler representation (NECS), which extracts stage-level code and Directed Acyclic Graph (DAG) Scheduler as training features. These features are then concatenated with configuration features (knob values), data features, and computing environment features as inputs to predict execution time by an MLP (Multi-Layer Perceptron) module. In its online recommendation phase, LITE introduces an Adaptive Candidate Generation module to initially construct a configuration set. This process involves utilizing a Random Forest Regression (RFR) model to ascertain the center of the promising knob range, which is determined based on factors such as the input data size and the specific application under consideration. Subsequently, the module establishes the knob searching boundary, derived from the input data. Once these boundaries are defined, the module randomly samples a small number of candidates from the selected search space. Finally, it evaluates the performance of each candidate configuration using the NECS model and recommends the knob values associated with the best-estimated performance. Meanwhile, NECS designs an Adaptive Model Update model to periodically finetunes the NECS model through adversarial learning when a predefined batch of new instances are collected. This paper is available on arxiv under CC BY 4.0 DEED. Authors: (1) Limeng Zhang, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia; (2) M. Ali Babar, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia. Authors: Authors: (1) Limeng Zhang, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia; (2) M. Ali Babar, Centre for Research on Engineering Software Technologies (CREST), The University of Adelaide, Australia. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 1.1 Configuration Parameter Tuning Challenges and 1.2 Contributions 1.1 Configuration Parameter Tuning Challenges and 1.2 Contributions 2 Tuning Objectives 2 Tuning Objectives 3 Overview of Tuning Framework 3 Overview of Tuning Framework 4 Workload Characterization and 4.1 Query-level Characterization 4 Workload Characterization and 4.1 Query-level Characterization 4.2 Runtime-based Characterization 4.2 Runtime-based Characterization 5 Feature Pruning and 5.1 Workload-level Pruning 5 Feature Pruning and 5.1 Workload-level Pruning 5.2 Configuration-level Pruning 5.2 Configuration-level Pruning 5.3 Summary 5.3 Summary 6 Knowledge from Experience 6 Knowledge from Experience 7 Configuration Recommendation and 7.1 Bayesian Optimization 7 Configuration Recommendation and 7.1 Bayesian Optimization 7.2 Neural Network 7.2 Neural Network 7.3 Reinforcement Learning 7.3 Reinforcement Learning 7.4 Search-based Solutions 7.4 Search-based Solutions 8 Experimental Setting 8 Experimental Setting 9 Related Work 9 Related Work 10 Discussion and Conclusion, and References 10 Discussion and Conclusion, and References 7.2 Neural Network Neural Network (NN)-based Solutions for automatic tuning leverage the power of artificial neural networks to model the complex relationships between configuration parameters and system performance, enabling efficient tuning without the need for exhaustive search or manual intervention. 7.2.1 NN-based solutions 7.2.1 NN-based solutions Tan et al. propose iBTune [15], individualized buffer tuning, to automatically reduce the buffer size for any individual database instance while still maintaining the quality of service for its response time. It leverages information from similar workloads to determine the tolerable miss ratio of each instance. Then, it utilizes the relationship between miss ratios and allocated memory sizes to individually optimize the target buffer pool sizes based on a large deviation analysis for the LRU caching model. To provide a guaranteed level of service level agreement (SLA), it designs a pairwise deep neural network (DNN) that predicts the upper bounds of the request response time by learning features from measurements on pairs of instances. Specifically, in the training phase, the NN network takes input of the performance metrics (logical reads, I/O reads, queries per second (QPS), CPU usage, miss ratio) of the target database instance and a similar database instance, the response time (RT) of the similar instance, and the encoding of the current time. The output of the network is the RT. In the testing phase, the previously observed sample of the target is selected as the similar instance. If the predicted RT meets the requirement, the computed new buffer pool size is sent for execution. Authors in [14] proposed Ottertune-DNN by adopting the OtterTune framework [8] and replacing its gaussian process model with a neural network model. Same to Ottertune [8], the raw data for each previous workload is collected and compared with the target workload. Data from the most similar previous workload are then merged with the target workload data to train a neural network model, which replaces the GP model in the original OtterTune. Finally, the algorithm recommends the next configuration to run by optimizing the model. The neural network model is a stacked 2-layer neural network with 64 neurons connected using ReLU as the activation function, and there is one dropout layer among the two hidden layers. Additionally, Gaussian noise is added to the neural network parameters to control the trade-off between exploration and exploitation, with increased exploitation throughout the tuning session achieved by reducing the scale of the noise. LITE [21] achieves configuration tuning for Spark applications by leveraging the power of NN to analyze the application code semantics as well as scheduling information during its execution. Its framework consists of an offline training phase to estimate the performance of a Spark application for a given knob configuration, and an online recommendation phase to recommend appropriate knobs for a given Spark application. In the offline training phase, LITE proposes a code learning framework, Neural Estimator via Code and Scheduler representation (NECS), which extracts stage-level code and Directed Acyclic Graph (DAG) Scheduler as training features. These features are then concatenated with configuration features (knob values), data features, and computing environment features as inputs to predict execution time by an MLP (Multi-Layer Perceptron) module. In its online recommendation phase, LITE introduces an Adaptive Candidate Generation module to initially construct a configuration set. This process involves utilizing a Random Forest Regression (RFR) model to ascertain the center of the promising knob range, which is determined based on factors such as the input data size and the specific application under consideration. Subsequently, the module establishes the knob searching boundary, derived from the input data. Once these boundaries are defined, the module randomly samples a small number of candidates from the selected search space. Finally, it evaluates the performance of each candidate configuration using the NECS model and recommends the knob values associated with the best-estimated performance. Meanwhile, NECS designs an Adaptive Model Update model to periodically finetunes the NECS model through adversarial learning when a predefined batch of new instances are collected. This paper is available on arxiv under CC BY 4.0 DEED. This paper is available on arxiv under CC BY 4.0 DEED. available on arxiv

Unlock Smarter DBMS Tuning with Neural Networks

If an individual is sleep deprived, at what minimum can certain functions continue without getting any sleep? If someone sees something from a distance, but it is just clear enough to be roughly interpreted by the mind in terms of kind, but not specificity, is there an input configuration requirement to guarantee an optimum interpretation of the external world by the human mind? If functions are continuously operating at minimums, could there be a likelihood that some of the factors responsible for optimum outputs may start getting the message that they are no longer necessary? If this is the case, could it cascade into a serious condition? Neurons are known to have around 50 billion proteins. Protein misfolding has been established as a major cause of some neurodegenerative diseases. A possible reason for protein misfolding has been identified as [cellular] environmental stress. A theoretical basis for why environmental stress may be responsible could be to look at working minimums and maximums, for functions, over certain intervals. Theorizing protein folding requires a top-down approach, which means that there is a source for which problems might arise, resulting--eventually--in misfolding and degenerative diseases. The closest destination for the top option is the electrical and chemical signals of neurons. It is theorized that the human mind is responsible for all functions that the brain is said to do. The human mind is the collection of all the electrical and chemical signals, with their interactions and features, in sets, in clusters of neurons, across the central and peripheral nervous system. This means that the human mind is the signals with their interactions and features. All the configurations for which representations and interpretations are based, for interoception and exteroception, have just one possible option in the brain, the signals, not genes, proteins, neurons, or other types of cells. This means that whatever is interpreted, accurately or not, or seems represented, accurately or not, is a result of the signals, such that with signals, interpretations, and features, in sets, are at the top, though their work has implications for other cells in the body, and several other molecules, especially proteins, abundant in neurons. Why? Exercise, for example, is an activity where electrical and chemical signals are interacting actively, with varying features applying. This top activity results in relays of electrical signals that, conceptually, for interactions with chemical signals, in sets, have an effect on other parts of the body. Simply, electrical and chemical signals are involved in every function. The consequences of those functions can also be seen elsewhere. Proteins, Neurons, and Signals Since neurons are not the human mind, or their proteins, because they do not organize information, it can be theorized that as neurons are involved in clusters, with sets of signals, their proteins assist several interactive processes between electrical and chemical signals. This indicates that when there are extended minimums or maximums, in sets of signals, there are ways that they come to have an effect on some of the proteins of the neurons involved in respective clusters [hence environmental stress]. Simply, neurons have proteins, and these proteins contribute to the primary role of signals, but as signals carry out their roles, depending on the pace or direction, they come to also have effects on the protein of some neurons, which may work more or work less, over an interval, which may, for some cases lead to misfolding, and then accumulations and disease, conceptually. It means that the mechanisms of signals can have an effect, conceptually, on the misfolding of proteins, then possibly developing into a degenerative disease for some. Tracking Possible Paths for Protein Misfolding From Signals It is possible to develop a number of minimums, maximums, and interactive-feature stretches of signals, with an exploration of how, for some people with Amyloidosis, that may have resulted from cellular [environmental] stress, to look at the roles that signals played. The interaction of signals is the way electrical signals strike at chemical signals, while the features are some of the states of the signals, in sets, at the times of the interactions. If a person drinks cold water but does not feel it as cold, why did the signals not give the experience of cold? There are several examples like this, but what can be looked at is the intensity of certain experiences or the longevity of others, which may have caused the larger protein folding error. Theorizing why proteins misfold may have to center around the major functional operators the electrical and chemical signals, which can then be sought, as the source toward reversal or prevention. There is a recent story in Nature, AI protein-prediction tool AlphaFold3 is now open source, stating that, "AlphaFold3, unlike its predecessors, is capable of modelling proteins in concert with other molecules. But instead of releasing its underlying code — as was done with AlphaFold2 — DeepMind provided access via a web server that restricted the number and types of predictions scientists could make. Crucially, the AlphaFold3 server prevented scientists from predicting how proteins behave in the presence of potential drugs. But now, DeepMind’s decision to release the code means academic scientists can predict such interactions by running the model themselves. The company initially said that making AlphaFold3 available only through a web server struck the right balance between enabling access for research and protecting commercial ambitions. Isomorphic Labs, a DeepMind spinoff company in London, is applying AlphaFold3 to drug discovery." There is a recent press release, Argonne team breaks new ground in AI-driven protein design, stating that, "Harnessing the power of artificial intelligence (AI) and the world’s fastest supercomputers, a research team led by the U.S. Department of Energy’s (DOE) Argonne National Laboratory has developed an innovative computing framework to speed up the design of new proteins. On the heels of this year’s Nobel Prize in Chemistry, which recognized advances in computational protein design, Argonne’s AI-driven approach has been selected as a finalist for the prestigious Gordon Bell Prize. Presented by the Association of Computing Machinery, the annual prize recognizes breakthroughs in using high performance computing to solve complex science problems. Mapping a protein’s amino acid sequence to its structure and function is a long-standing research challenge. Each unique arrangement of amino acids — the building blocks of proteins — can yield different properties and behaviors. The sheer volume of potential variations makes it impractical to test them all through experiments alone. To put this in perspective, modifying just three amino acids in a sequence of 20 creates 8,000 possible combinations. But most proteins are far more complex, with some research targets containing hundreds to thousands of amino acids." If an individual is sleep deprived, at what minimum can certain functions continue without getting any sleep? If someone sees something from a distance, but it is just clear enough to be roughly interpreted by the mind in terms of kind, but not specificity, is there an input configuration requirement to guarantee an optimum interpretation of the external world by the human mind? If functions are continuously operating at minimums, could there be a likelihood that some of the factors responsible for optimum outputs may start getting the message that they are no longer necessary? If this is the case, could it cascade into a serious condition? Neurons are known to have around 50 billion proteins . Protein misfolding has been established as a major cause of some neurodegenerative diseases . A possible reason for protein misfolding has been identified as [cellular] environmental stress . A theoretical basis for why environmental stress may be responsible could be to look at working minimums and maximums, for functions, over certain intervals. have around 50 billion proteins major cause of some neurodegenerative diseases as [cellular] environmental stress Theorizing protein folding requires a top-down approach, which means that there is a source for which problems might arise, resulting--eventually--in misfolding and degenerative diseases. The closest destination for the top option is the electrical and chemical signals of neurons. It is theorized that the human mind is responsible for all functions that the brain is said to do. The human mind is the collection of all the electrical and chemical signals, with their interactions and features, in sets, in clusters of neurons, across the central and peripheral nervous system. This means that the human mind is the signals with their interactions and features. All the configurations for which representations and interpretations are based, for interoception and exteroception, have just one possible option in the brain, the signals, not genes, proteins, neurons, or other types of cells. This means that whatever is interpreted, accurately or not, or seems represented, accurately or not, is a result of the signals, such that with signals, interpretations, and features, in sets, are at the top, though their work has implications for other cells in the body, and several other molecules, especially proteins, abundant in neurons. Why? Exercise, for example, is an activity where electrical and chemical signals are interacting actively, with varying features applying. This top activity results in relays of electrical signals that, conceptually, for interactions with chemical signals, in sets, have an effect on other parts of the body. Simply, electrical and chemical signals are involved in every function. The consequences of those functions can also be seen elsewhere. Proteins, Neurons, and Signals Since neurons are not the human mind, or their proteins, because they do not organize information, it can be theorized that as neurons are involved in clusters, with sets of signals, their proteins assist several interactive processes between electrical and chemical signals. This indicates that when there are extended minimums or maximums, in sets of signals, there are ways that they come to have an effect on some of the proteins of the neurons involved in respective clusters [hence environmental stress]. Simply, neurons have proteins, and these proteins contribute to the primary role of signals, but as signals carry out their roles, depending on the pace or direction, they come to also have effects on the protein of some neurons, which may work more or work less, over an interval, which may, for some cases lead to misfolding, and then accumulations and disease, conceptually. It means that the mechanisms of signals can have an effect, conceptually, on the misfolding of proteins, then possibly developing into a degenerative disease for some. Tracking Possible Paths for Protein Misfolding From Signals It is possible to develop a number of minimums, maximums, and interactive-feature stretches of signals, with an exploration of how, for some people with Amyloidosis, that may have resulted from cellular [environmental] stress, to look at the roles that signals played. The interaction of signals is the way electrical signals strike at chemical signals , while the features are some of the states of the signals, in sets, at the times of the interactions. If a person drinks cold water but does not feel it as cold, why did the signals not give the experience of cold? There are several examples like this, but what can be looked at is the intensity of certain experiences or the longevity of others, which may have caused the larger protein folding error. The interaction of signals is the way electrical signals strike at chemical signals Theorizing why proteins misfold may have to center around the major functional operators the electrical and chemical signals, which can then be sought, as the source toward reversal or prevention. There is a recent story in Nature , AI protein-prediction tool AlphaFold3 is now open source , stating that, "AlphaFold3, unlike its predecessors, is capable of modelling proteins in concert with other molecules. But instead of releasing its underlying code — as was done with AlphaFold2 — DeepMind provided access via a web server that restricted the number and types of predictions scientists could make. Crucially, the AlphaFold3 server prevented scientists from predicting how proteins behave in the presence of potential drugs. But now, DeepMind’s decision to release the code means academic scientists can predict such interactions by running the model themselves. The company initially said that making AlphaFold3 available only through a web server struck the right balance between enabling access for research and protecting commercial ambitions. Isomorphic Labs, a DeepMind spinoff company in London, is applying AlphaFold3 to drug discovery." Nature AI protein-prediction tool AlphaFold3 is now open source There is a recent press release, Argonne team breaks new ground in AI-driven protein design , stating that, "Harnessing the power of artificial intelligence (AI) and the world’s fastest supercomputers, a research team led by the U.S. Department of Energy’s (DOE) Argonne National Laboratory has developed an innovative computing framework to speed up the design of new proteins. On the heels of this year’s Nobel Prize in Chemistry, which recognized advances in computational protein design, Argonne’s AI-driven approach has been selected as a finalist for the prestigious Gordon Bell Prize. Presented by the Association of Computing Machinery, the annual prize recognizes breakthroughs in using high performance computing to solve complex science problems. Mapping a protein’s amino acid sequence to its structure and function is a long-standing research challenge. Each unique arrangement of amino acids — the building blocks of proteins — can yield different properties and behaviors. The sheer volume of potential variations makes it impractical to test them all through experiments alone. To put this in perspective, modifying just three amino acids in a sequence of 20 creates 8,000 possible combinations. But most proteins are far more complex, with some research targets containing hundreds to thousands of amino acids." Argonne team breaks new ground in AI-driven protein design

Stories, News & Mentions about NEU

Neu’s Stories on HackerNoon

Neu's News & Mentions