Hi. We’re Plastiq. We help growing businesses improve cash flow with instant access to working capital and a time time saving bill pay solution. We also help SMBs get paid faster with free credit card acceptance. For platforms and marketplaces serving SMBs, our embedded finance solutions enable any business to offer a payment solution to their customers. With inflation on the rise, paying suppliers fast and getting paid earlier is a competitive edge. At Plastiq, we offer a way to pay suppliers by your preferred method regardless of acceptance, eliminating the friction in B2B payments. Get our playbook on scaling your business by accelerating the cash conversion cycle here: https://www.plastiq.com/ccc-playbook/

Plastiq

The fight against microplastics in our oceans is a crucial environmental challenge, and Artificial Intelligence (AI) is emerging as a powerful tool in this battle. Microplastics, tiny plastic fragments less than five millimeters in size, pose a significant threat to marine life and ecosystems. They originate from various sources, including larger plastic debris that degrades over time, and microbeads used in cosmetics and other products. Their small size makes them difficult to detect and remove, which is where AI steps in. AI technologies, particularly in the form of machine learning and data analytics, are being employed to identify, track, and ultimately remove microplastics from marine environments. For example, AI algorithms can analyze water samples and images from drones or satellites to detect microplastics concentrations. This data can then be used to map pollution hotspots and track the movement of these particles through ocean currents. Startups are at the forefront of integrating AI into ocean cleanup efforts. Companies like The Ocean Cleanup, a Netherlands-based organization, are using AI to enhance their systems that collect plastic from rivers and oceans. Their technology uses machine learning to optimize the efficiency of cleanup devices and predict the accumulation of plastics. Another innovative approach is the use of autonomous robots equipped with AI for cleaning up microplastics. These robots navigate water bodies, identify microplastics using onboard sensors, and collect them without human intervention. This not only increases the scale of cleanup operations but also reduces the risks and costs associated with manual collection. In addition to direct cleanup efforts, AI assists in preventive measures. By analyzing data on plastic usage and waste management practices, AI helps identify key areas where interventions reduce the entry of plastics into the ocean. This includes optimizing recycling processes and developing more effective waste management strategies. Startups further contribute to solving the microplastics problem by focusing on the source of these pollutants. Innovations in biodegradable materials significantly reduce the amount of plastic entering the oceans. AI accelerates research and development in this area by analyzing material properties and environmental impacts, helping to create sustainable alternatives to conventional plastics. Moreover, public awareness and behavioral change are critical in combating microplastic pollution. AI-powered apps and platforms play an important role in educating the public and promoting eco-friendly habits. For instance, apps that track an individual's plastic usage and provide tips for reducing their plastic footprint are considered to be an effective tool for change.Beyond the pollution itself, a key study featured recently highlights the alarming risks associated with pathogen-laden microplastics in aquatic environments, raising significant public health concerns. This research explores how microplastics serve as carriers for pathogens in various water bodies, examining factors that influence the adherence and survival of these pathogens on microplastics, and their potential transmission to humans. The study is crucial for informing public health policies and environmental strategies, emphasizing the need for increased monitoring of microplastic pollution. It calls for further research into how microplastics facilitate the spread of pathogens and the resulting health risks. The study underscores the critical importance of understanding the role microplastics play in pathogen distribution, highlighting its significant implications for both environmental and human health. The research brings attention to the often-overlooked health dangers posed by pathogens on microplastics in water, advocating for urgent actions to safeguard public health and environmental integrity. The study also stresses the need for multidisciplinary research to better understand the complex interactions between microplastic-associated pathogens and to develop effective mitigation strategies. The role of AI in fighting microplastics in our oceans is multifaceted, encompassing detection, cleanup, prevention, and public engagement. As technology advances, startups specializing in AI and environmental solutions are poised to make significant contributions to preserving marine ecosystems and protecting the health of our oceans. By combining innovative technologies with concerted efforts across sectors, the goal of a cleaner, plastic-free ocean becomes increasingly attainable.

AI is Helping Clean Our Oceans of Plastics

PROBLEM STATEMENT Marine plastic pollution has been at the forefront of climate issues for the past decade. Not only does plastic in the ocean capable of killing marine life by strangulation or starvation but it is also a major factor in warming the ocean by trapping CO2. In recent years, there have been numerous attempts at cleaning the plastic that has been circling our oceans such as by the non-profit group, The Ocean Cleanup. The problem with a lot of cleanup processes is that it requires human labor and is not cost-efficient. There has been a lot of research done to automate this process by using Computer Vision and Deep Learning to detect marine debris to utilize ROVs and AUVs for cleanup. Note: This is theoretical and we are working on publishing our paper. Once it gets peer-reviewed and gets published in a journal I will update this article. So, watch this space for the release of our academic paper! : , , and Reading Resources Our Paper on Using CV and DL to detect Epipelagic plastic The University Of Minnesota's paper on a general-purpose marine debris detecting algorithm The Ocean Cleanup’s paper on floating plastic detection on rivers. The major issue for this approach is regarding the availability of datasets to train the computer vision models. The JAMSTEC-JEDI dataset is a good collection of Marine Debris off the coast of Japan on the seafloor. But, apart from this dataset, there is a huge discrepancy in the availability of datasets. For this reason, I’ve utilized the help of Generative Adversarial Networks; The DCGAN in particular to curate synthetic datasets that could theoretically be a close replica to real datasets over time. (I wrote theoretically because there are a lot of variables such as quality of real-images available, progress with GANs, training, etc). GAN and DCGAN GANs or Generative Adversarial Networks were proposed by Ian Goodfellow et al in 2014. GANs consist of a simple 2 components called Generators and Discriminators. An oversimplification of the process is as follows: The Generators role is to generate new data and the Discriminators role is to distinguish between the generated data and the actual data. In the ideal scenario, the discriminator is unable to distinguish between the generated data and real data which results in ideal synthetic data points. DCGAN is a direct extension of the GAN architecture mentioned above except it uses Deep Convolutional Layers in the discriminator and generator respectively. It was first described by Radford et. al in the paper . The discriminator is made up of strided convolutional layers while the generator is made up of convolutional transpose layers. Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks GAN architecture (source: ) Here PyTorch Implementation In this method, we are going to be applying the DCGAN architecture on the dataset. If you’re not familiar with the DeepTrash dataset, consider reading my paper . DeepTrash is a collection of plastic images in the epipelagic layer and abyssopelagic layer of the ocean curated for marine plastic detection using computer vision. DeepTrash A Robotic Approach towards Quantifying Epipelagic Bound Plastic Using Deep Visual Models Let's begin coding! Installing Requirements We start by installing all the basic requirements to building our GAN model such as Matplotlib and Numpy. We will also be utilizing all the tools (such as neural networks, transformations) from Pytorch. If you’re not familiar with PyTorch I recommend giving this article a read: Initializing our Hyperparameters This step is fairly straightforward. We’re going to set up the hyperparameters that we want to train the Neural Network with. These hyperparameters are borrowed straight from the paper and PyTorch’s tutorial on training GANs. Generator and Discriminator Architectures Now, we define the architectures for the generator and discriminator. Defining the Training Function After defining the Generator and Discriminator classes, we move on to defining the training function. The training function takes in the generator, discriminator, optimization functions, and the number of epochs as the arguments. We train the generator and discriminator by recursively calling the train function until the required number of epochs. We do this by iterating through the dataloader and updating the discriminator with new images from the generator and calculating and updating the loss function. Monitoring and Training the DCGAN After we’ve established the Generator, Discriminator, and Train functions the final step is to simply call the train function for the number of epochs we defined. I’ve also used which allows us to monitor our training. Wandb Results We plot the loss incurred by the generator and discrimination during training. IMG - Generator and Discriminator Loss during Training We can also pull up an animation of how the generator was generating images to see a difference between the real and the fake images. Which looks something like this: And the final resulting image after training (the same image as above). CONCLUSION In this article, we discussed the use of Deep Convolution Generative Adversarial Networks to generate synthetic images of marine plastic that can be used by researchers to extend their current dataset of marine plastic. This can help with giving researchers the ability to extend their dataset with a mix of real and synthetic images. As you can see with the results, the GAN still needs a lot of work. The ocean is a complex environment with varying illumination, turbidity, blur, etc. But this is a theoretical starting point that other researchers can build off of. If you’re interested in improving the results and building a better network architecture, please reach out to me at gautamtata.blog@gmail.com.

Synthesizing Images of Marine Plastic Using Deep Convolutional Generative Adversarial Networks

Along with my team, I’ve been involved in a project called , a novel approach that uses Deep Learning to identify marine-plastic and I wanted to share the findings: DeepPlastic 85% mean-average precision! Using our model, we can now detect on average 85% (mAP) of all epipelagic plastic in the ocean. We achieve this level of precision based on a Neural Network architecture called . Below we’ve attached a video containing examples of marine plastic that we’ve run our model on: YOLOv5-S Where’s the Paper and The Code? This article would mainly serve as a no-code summary of our research paper. If you’d like to skip straight to the nitty-gritty details of the neural network or the code, you can access them here: arxiv pre-print: https://arxiv.org/abs/2105.01882 Codebase and Dataset: https://zenodo.org/record/5562940#.YY1uML3MI-R If you’d like me to write another blog post explaining the code, data augmentation, etc., let me know in the comments below! How Did I Get Involved In This? I’ve always been passionate about the oceans. After graduating from school at California State University, Monterey Bay, I knew that I wanted to build tools/software that can help protect the ocean. After I collected, annotated, and curated the data along with the model, I realized that the precision metrics were significant, and there could be a manuscript that could be published here. So, I asked for help from , an expert in Marine plastics, and and for help with the writing and publishing of the manuscript. Dr. Sara-Jeanne Royer Jay Lowe Olivier Poirion Abstract The quantification of positively buoyant marine plastic debris is critical to understanding how concentrations of trash gather across the world’s oceans and identifying high concentration garbage hotspots in dire need of trash removal. Currently, the most common monitoring method to quantify floating plastic requires the use of a manta trawl. Before analysis, the need for physical removal incurs high costs and requires intensive labor–preventing scalable deployment of a real-time marine plastic monitoring service across the oceans. Without better monitoring and sampling methods, the total impact of plastic pollution on the environment as a whole, and details of impact within specific oceanic regions, will remain unknown. This study presents an automated workflow that utilizes videos and images captured within the epipelagic layer of the ocean as input and produces real-time quantification of marine plastic for accurate quantification and removal. YOLOv5-S was the best performing model, which operates at a Mean Average Precision (mAP) of 0.851 and an F1-Score of 0.89 while maintaining near real-time speed. In addition, our method can utilize” off the shelves” camera equipment and standard low-cost GPUs to monitor/quantify epipelagic plastic in near real-time. Goal For The Project We wanted to build a generalized object detector capable of identifying and quantifying sub-surface plastic around the world. Now that we understand our goal and how to achieve it, let us jump into the workflow. Curating The Dataset Finding a dataset that contained annotated pictures of marine debris was incredibly hard. There was no dataset in existence that had images of marine plastic in the epipelagic layer of the ocean. So, I decided to create one. I bought a GoPro Hero 9, A wetsuit, and snorkeling equipment and headed out to various locations in California along with 2 Plastic bags and 2 Plastic Bottles. The locations I visited were: Lake Tahoe, Bodega Bay, San Francisco Bay. Here, I shot videos of the plastic in 4K and later broke them into images frame-by-frame. [All plastics used were sanitized and were removed from the environment after I finished capturing the videost] The initial dataset was more than 100,000 images which I then painstakingly went through one by one and chose the best images and annotated them using supervise.ly. The final dataset, along with images scraped from the internet, was a whopping 4000 images. I tried my best to replicate real-world scenarios such as occlusion and brightness by burying objects in sand or placing them across from the sun. ( ) Photo by on ; ( ) Photo by on ; ( ) Image by Author Bottom Right Naja Bertolt Jensen Unsplash Top Right Nariman Mesharrafa Unsplash Top Left, Bottom Right Data Formatting Images were resized into 416x416 and converted into the format the Darknet and YOLOv5 PyTorch require. Data Augmentation Since the final dataset only contained 4000 images, I thought the best way to increase the size of the dataset was to augment it. So, I used Flip, Rotate, Brightness to replicate oceanic environments. I also used B&W to make the model not generalize towards color and cutouts to simulate occlusion. Building the Neural Network Building a Neural Network was a straightforward task. I had two goals for model selection: The model had to be somewhat accurate, and the model had to be fast. Fast enough to be used on Buoys and UAVs. I tried many models, such as Faster R-CNN, EfficientDet, SSD, etc., but stuck with two models: YOLOv4-Tiny and YOLOv5-S. Interested in a code run down for YOLOv5? Let me know in the comments below or reach out to me. Things to know/Tuning Hyperparameters: I used an called ADAM to set a decaying learning rate.Used a package called (Weights and Biases) and continuously monitored the loss.I used a as the final layer and only used called trash_plastic.I used paperspace.com and Google Colab pro with to train the model.Used transfer learning from weights trained on and Adaptive Learning Rate W&B softmax a single class NVIDIA v100 GPUs Underwater Scenes Deep Sea Debris — JAMSTEC JEDI Dataset. All the code used for the models including architectures can be found at , YOLOv4 YOLOv5 Interested in our code? Find it here Results After a lot of experimenting with training methods, data augmentations, and fine-tuning hyperparameters, we finally reached a point where the results were good enough to be used in real-world deployments. Best model : Precision: 96%, Mean-Average-Precision: 85%, F1-Score: 0.89, Inference Speed: 2.1 milliseconds/img. YOLOv5-S Photos by , ( ) Photo by on ; All Other Images by Author (Bottom Row) JAMSTEC JEDI (Second Row First Image) Bottom Right Naja Bertolt Jensen Unsplash What’s Next? At the moment, we are in the process of getting our paper published. We are trying to get the model in the hands of other researchers for testing and developing innovative ways to synthesize more data. If you’re interested, want to contribute, or want to chat, You can reach me here: . gautamtata.blog@gmail.com This article was first published here

How Deep Learning Can Help Quantify, Monitor, and Remove Marine Plastic: The DeepPlastic Way

Fashion brands worldwide are striving to reduce the industry’s negative environmental impact by creating new clothing using only recycled materials. This practice supports a circular economy, which gives used materials that already exist in our world a new life, thus avoiding landfills. Recently, there has been a growing movement in fashion production to create unique pieces using recycled plastic. Sounds great, right? Image via @milk on Instagram Plastic in our Oceans Eight million metric tons of plastics enter our oceans each year, severely impacting the biodiversity within marine environments. Whether it’s plastic straws, bottles, or bags, this is incredibly problematic because these plastic materials are not biodegradable. This means these materials will not leave our waters unless we physically remove them. Environmentalists and organizations worldwide are trying to come up with ways to prevent plastics from entering the ocean and ways to remove and reuse what is already there. The Role of the Fashion Industry A growing movement in the fashion industry is shifting towards a circular approach, to reverse the damage caused by the industry’s practices thus far. For instance, it is estimated that 92 million tonnes of textile waste are created every year globally, which ends up in our landfills or is burned into the atmosphere. Fashion brands are investing in technology that can produce products made entirely from recycled materials, as well as in systems that will help us recycle our used clothing in a more sustainable way. Currently, only about 3% of used clothing is recycled and used to create new clothes. This is because certain fabrics like wool and cotton are extremely challenging to recycle. The fabrics our clothing is currently made up of are very complex since whole products are made up of a blend of different materials that cannot be separated. The infrastructure and technology needed to complete this recycling process are also too new. Therefore, companies are looking for other materials, like plastic water bottles, to recycle into new pieces in a more efficient and sustainable way. It is now more accessible than ever to find clothing made from recycled plastics. How Does a Plastic Bottle Turn into a Clothing Item? The concept of turning plastic into clothing may seem like a complicated process, so let’s break it down. Using plastic water bottles removed from the ocean as our material of choice, the process starts with these bottles being sorted by color. This is because often only clear bottles can be used to make clothing. Once the sorting is complete, caps are removed and materials are sanitized. Then the bottles are broken down and shredded into small flakes. These flakes are then melted and spun into fine threads, which are spun together again to create yarn. This yarn can then be sewn into clothes to make various items ranging from swimwear to jackets, to activewear, to socks. Once the product is created, it then goes through other design processes such as color dyeing. Gif via @lucamainini The Issue of Microfibers On the surface, making clothing out of recycled plastics may seem like a great idea, but environmentalists have been digging deeper into the negative effects of this practice. It has been discovered that washing clothes made from recycled plastic can cause the shedding of non-biodegradable microfibers. Microfibers are essentially very tiny pieces of plastic that can shed off clothing. They are released into our water systems and can harm the biodiversity within them. These microfibers are rarely removed from the oceans because of their minuscule size. Technology is not quite there yet to filter out these microfibers before they reach the water systems. This filtration system could eventually be implemented into our washing machines to attempt to solve this problem. Girlfriend Collective - known for their activewear made from recycled plastic, now sells a Microfiber filter that you can install on your washing machine. Another good option is to wash your synthetics fabrics in a washing bag. Brands are also researching ways to reduce the microfiber release of their products. Be Mindful of Consumption Habits While clothes made from recycled plastics are an innovative way to repurpose plastics that already exist, the most effective solution to protecting the environment is to reduce our consumption habits. Overconsumption and waste is a major issue in the fashion industry. For instance, in North America, around 85% of clothing goes directly to the landfill, rather than be recycled or reused. The energy needed to produce and transport these clothing pieces made from recycled items is also damaging. So, it is important to be mindful of our purchases and invest in quality pieces that we are going to wear long-term to avoid excessive waste. Again, this circular approach to fashion is a fantastic way to support our environment, but this must be done in tandem with a reduction in our consumption. Image via @giambattistavalliparis on Instagram Shopping Second-Hand is Always a Great Option Shopping second-hand is another great way to affordably support circular fashion, as you are giving an item a new life and keeping it from the landfills. You can incorporate new items into your wardrobe while also protecting the planet. A lot of the time you can find high-quality gems at a fraction of the cost, just by shopping second-hand. Image credits: Vin + Omi @milk on Instagram @lucamainini @giambattist @giambattistavalliparis on Instagram Originally published . here

Sustainable Clothes Made From Recycled Plastic

A 25-year-old Dutchman named Boyan Slat, alternately hailed as by the publication Maritime Executive, has for years waged war against plastic pollution in the world’s oceans. “an ocean action hero” and a “wunderkind” It is a foe, Maritime Executive noted, that is “intent on taking over the planet,” which is unfortunately not hyperbole. According to the United Nations, some of plastic waste winds up in the oceans each year, and over time it breaks down into microplastics. There are some of the latter material beneath the waves, according to a recent study by the Commonwealth Scientific and Industrial Research Organization (CSIRO), and it poses a threat to marine life, and by extension global food chains. eight million tons 16 million tons Slat, who at age 18 founded a nonprofit known as The Ocean Cleanup, first centered his efforts on the , an area twice the size of the state of Texas that stands as the world’s largest concentration of plastic pollution. Now he has turned his attention to the world’s rivers, the source of much of the plastic that finds its way to the oceans. Great Pacific Garbage Patch His weapons of choice are robotics -- starting with a 2,000-foot-long unmanned floating barrier . While the U-shaped apparatus failed on its initial foray toward the Garbage Patch, splitting in two late in 2018, an overhauled version of the same structure was launched in June 2019. It succeeded in bringing home some , which was recycled and beginning in October 2020. The proceeds will be used to fund subsequent cleanup efforts. given the name Wilson 60 bags of trash sold as sunglasses As for the rivers, Slat’s organization earlier this year deployed called “Interceptors” to waterways in Malaysia, Indonesia and the Dominican Republic, with plans to hit the world’s 1,000 most polluted rivers by 2025. solar-powered autonomous trash collectors "We accept that we won't deliver magic in one go,” he told CNN. “But we're doing this, step by step." Slat is far from alone in using robotics in the fight against pollution. Other enterprises have, in fact, developed bots that can or . While these robots might not look as futuristic as robots in classic sci-fi movies, they have proven to be effective, no matter their use. consume water pollution collect river trash those that can plant trees 10 times faster than humans to those that can monitor plant growth in adverse weather conditions. From those that can monitor coral reefs to those that can kill invasive species, and even those that venture into sewers to reduce carbon emissions. They range from Particularly important are those robots used to alleviate air pollution, which according to the World Health Organization around the world every year, and leaves 90 percent of the global population breathing unhealthy air. That led the Integral Platform for Climate Initiatives to partner with Russia’s ITMO University in 2018 to develop to monitor air quality (as well as bots to gather data about water quality). kills seven million people drones equipped with sensors Similarly equipped drones were in 2019, as air pollution is a particularly serious problem there. While air-quality evaluations had previously been performed by those on the ground, the drones’ sensors allowed for an in-depth examination of such things as air temperature, atmospheric pressure, humidity and levels of various gases, including carbon monoxide and carbon dioxide. tested in Greece And in Thailand, meanwhile, a fleet of drones was deployed in 2019, in an attempt to spray pollution out of the sky. These aircrafts dispensed water and a “non-hazardous chemical spray,” , and government officials claimed that the drones were able to lower the level of a particularly harmful toxin. according to the Bangkok Post But robotics are truly poised to make a wide-ranging impact. Consider, for example, the developed by MIT in partnership with the Woods Hole Oceanographic Institution (WHOI). They measure ocean depth, detect leaked chemicals or collect other samples of interest. While previous efforts in this realm have suffered from a lack of efficiency or accuracy -- i.e., the robots tended to explore uninteresting areas and/or net useless samples -- this updated technology uses probability to find the most promising places. robotic boats One robotic boat found the most exposed part of a coral reef in Barbados -- crucial to assessing the impact of climate change -- and another collected as many as eight times as many samples as previous methods. Victoria Preston, one of the authors of a 2019 paper on robotic boats, that with the older technology, “it’s easy to think you’ve found gold, but really you’ve found fool’s gold.” Now, that is far less likely. told SciTechDaily Elsewhere, robots have helped improve factories through automated processes that measure energy efficiency and environmental dangers. Through IoT-based monitoring robots can assess toxicity levels in factories and on the field. This type of can reduce greenhouse gas emissions and waste. Robots can even sort through materials to determine which parts can be recycled. environmental monitoring But back to Slat for just a moment. According to a , the problem posed by plastic pollution first caught his attention when at age 16 he saw more plastic bags than fish during a diving trip to Greece. He set aside his aerospace engineering studies to . He now serves as its CEO. 2018 Time Magazine profile found The Ocean Cleanup in 2013 While Slat’s organization, The Ocean Cleanup, has done its part to advance the robotics used in the fight against pollution, Slat is fully aware that the problem won’t be eradicated anytime soon. “Big problems,” he told Time, “require big solutions.” Certainly there will be a need for even bigger solutions. But suffice it to say that the awareness is there, as is the resolve. It is as important a battle as any, and one humankind cannot afford to lose.

The Future Is Now: Robots Helping Us Combat Plastic Pollution And Climate Change

Zuleyka Strasner's honeymoon was a life-changing experience, and not just because she was newly married. What was meant to be a romantic vacation in Nicaragua became the catalyst for her transforming her lifestyle and founding her own company. The Corn Islands were beautiful, Zuleyka remembers. But the ocean was a stark reminder of the world's state of pollution and waste. "I was astounded by how much plastic and trash there was in the sea, absolutely astounded," Zuleyka says. When she returned home to San Francisco, she got rid of all single-use plastic in her home. She cleaned out her kitchen cupboards. Her grocery trips turned into three-hour adventures. And she realized exactly how challenging it was to live an environmentally conscious lifestyle. So, Zuleyka decided to take matters into her own hands. In 2018, she founded , a plastic-free online grocery store in the Bay Area of California. Zero Grocery It wasn't easy, especially since Zuleyka began without any capital. But she eventually raised $4.7 million within two years. In an episode of How I Raised it, Zuleyka tells the story of how she went from $2,500 of her own money to turning down checks in 2020. Use your connections (and don’t feel shame) When Zuleyka felt ready to begin raising money in 2018, she thought she'd meet with maybe 20 people. A few might cut her some checks and she'd be good to go, she assumed. In reality, she presented 263 pitches between September and January — a five month timespan — all on her own. Throughout the fundraising process, Zuleyka made use of her secret weapon: Connections. Since she previously worked as an operations manager at Felicis Ventures, she had the contacts she needed to set up meetings. "I had an early network, I knew a lot of VCs, I knew a lot of angels, I had made just a lot of friends because I like people. And I also have little to no shame," Zuleyka says. When one potential investor turned her down, she asked them for more names: "Each one person can unlock for me another three or four people ... You just keep that pipeline going," Zuleyka says. It was that boldness that led to her success. During that hectic first round, she raised $500,000 from six investors. Don't waste your time with those who don't care Over the course of her 263 meetings, Zuleyka spoke to a drove of potential investors. "There were some people I really tried hard to win over and over and over again," Zuleyka says. "And the honest answer is they're just not that into you … they're just not that into your company." Instead, save your energy for the people who legitimately care. For Zuleyka, that person was Charles Hudson. Hudson ( on the How I Raised It podcast), managing partner at Precursor Land Ventures, believed in Zuleyka from the get go. He seemed genuinely interested in her, how she operated, and the idea behind Zero Grocery. In the end, half of that initial $500,000 came from Hudson. who also appeared Underdogs have superpowers Zuleyka, a black trans woman from East London, is not what the majority of Silicon Valley looks like. She never brings this up in pitch meetings: "It really isn't the basis of any of the discussions that we have, nor is it the basis on which I'm building this company at all. So I don't really ascribe to any of that identitarian politics at all, but it is important for us to recognize." When it came time for Zero Grocery to hire employees, Zuleyka looked to people from a variety of backgrounds, but especially those who had struggled or suffered in some way. She values the "true underdogs" who may have been overlooked in the past. These individuals bring an intense will to succeed, which Zuleyka considers a superpower. 35X growth isn’t easy, so you have to stay resilient Zuleyka recalls times when Zero Grocery was days and even hours within shutting down completely. But she always pulled through. Her persistence was especially put to the test during the first round of fundraising, when she spent her days in and out of meetings. Not every potential investor liked her ideas; some dismissed or tore her mission up completely. But "every meeting you go into, you cannot take the baggage from the last meeting," she says. Ultimately, it was Zuleyka's belief that her company was doing something good for the world that kept her resilience intact. In 2020, the company grew 35X. By the end of the year, Zero Grocery had nearly 100 employees, up from six workers in March. A large component of the company's fundraising success — and the massive growth of its customer base — was due to the COVID-19 pandemic. With people avoiding public spaces, more and more individuals turned to online grocery shopping. And that meant more and more people found Zero Grocery. "If I could click my fingers and this would all be over tomorrow, I would do it instantly," Zuleyka says. But at the same time, she recognizes that Zero Grocery has provided a useful purpose to many: "We've at least been able to take up that responsibility to service people and service folks and enable them to not leave their homes." Zuleyka feels hopeful about the future of Zero Grocery. "Maybe it's bliss, ignorance or being blind, I'm not sure. But it's incredible what the human spirit can do," Zuleyka says. "This company, this idea, this mission is so much bigger than me." Nathan Beckord is the CEO of Foundersuite.com which makes software for raising capital. Foundersuite has helped startups raise over $3 billion in angel and venture capital since 2016. This article is based on an episode of Foundersuite’s How I Raised It podcast , a behind-the-scenes look at how startup founders raise money.

How An "Underdog" Founder Raised $4.7 Million To Build A Plastic-Free Grocery Delivery Service

Odei Garcia-Garin et al. from the University of Barcelona have developed a deep learning-based algorithm able to detect and quantify floating garbage from aerial images. They also made a web-oriented application allowing users to identify the garbage known as floating marine macro-litter, or FMML, within images of the sea surface. Watch the video: References Odei Garcia-Garin et al., Automatic detection and quantification of floating marine macro-litter in aerial images: Introducing a novel deep learning approach connected to a web application in R, Environmental Pollution, ​. https://doi.org/10.1016/j.envpol.2021... Code & web app: https://github.com/amonleong/MARLIT Follow me for more AI content: Instagram: ​ https://www.instagram.com/whats_ai/ LinkedIn: ​ https://www.linkedin.com/in/whats-ai/ Twitter: ​ https://twitter.com/Whats_AI Facebook: ​ https://www.facebook.com/whats.artifi... Medium: ​ https://whats-ai.medium.com/ Join Our Discord channel, Learn AI Together: ​ https://discord.gg/learnaitogether The best courses in AI & Guide+Repository on how to start: ​ ​ https://www.omologapps.com/whats-ai ​ https://github.com/louisfb01/start-ma... Become a member of my YouTube community: ​ https://www.youtube.com/channel/UCUzG... Chapters: 0:00​ - Hey! Tap the Thumbs Up button and Subscribe. You'll learn a lot of cool stuff, I promise. 0:30​ - Floating marine macro-litter 2:19​ - The method 5:10​ - Conclusion Video Transcript 00:00 an ai software able to detect and count 00:03 plastic waste in the ocean 00:04 using ariel images it's both clever and 00:07 simple 00:08 and you could use this same model for 00:10 many image classification applications 00:12 let's see how it works 00:16 [Music] 00:21 this is what's ai and i share artificial 00:23 intelligence news every week 00:25 if you are new to the channel and want 00:26 to stay up to date please consider 00:28 subscribing to not miss any further news 00:31 we live on a blue planet over 70 00:35 of earth is covered by sea from space 00:38 our ocean appears pristine clean 00:42 unfortunately it's not because of poorly 00:45 controlled waste sites 00:46 illegal dumping and mishandled waste 00:49 from population centres 00:51 tourism industrial and agricultural 00:53 activities 00:54 an estimated 8 million metric tons of 00:57 plastic 00:58 waste entered the oceans 01:02 aude garcia garion et al from the 01:04 university of barcelona 01:06 have developed a deep learning based 01:08 algorithm able to detect and quantify 01:10 floating garbage from aerial images 01:13 they also made a web-oriented 01:15 application allowing users to identify 01:17 these garbages 01:18 called floating marine microliter or fml 01:21 within 01:22 images of the sea surface floating 01:25 marine macro litter is any persistent 01:27 manufactured or processed solid material 01:30 lost or abandoned in a marine 01:32 compartment as you most certainly know 01:34 these plastic wastes are dangerous for 01:36 fish turtles and marine mammals as they 01:39 can either 01:40 ingest them or get entangled and hurt 01:42 traditional approaches to detecting 01:44 these 01:45 fmls are observer-based methods 01:48 meaning that they require someone on a 01:50 vessel or airplane to look for them 01:52 yielding to precise identification but 01:55 extremely expensive and time demanding 01:57 labor 01:58 fortunately this detection can be done 02:00 using cameras or sensors on aerial 02:02 vehicles 02:03 but it also requires trained scientists 02:05 to manually look at the collected data 02:08 being again extremely time consuming 02:10 automation is clearly needed here and 02:12 could help us 02:13 improve the quality of our marine 02:15 compartments worldwide 02:16 much more effectively this is where 02:19 machine learning 02:20 and deep learning commonly deep learning 02:23 proves over and over 02:24 that it's a very powerful automation 02:26 tool and especially in the computer 02:28 vision industry 02:29 where it's known to automatically 02:31 identify the important features of an 02:33 image 02:33 without any human supervision making 02:36 this approach 02:37 less time demanding than its 02:38 predecessors for many different 02:40 applications including 02:41 this very important one as you may 02:44 suspect 02:45 they use the convolutional neural 02:46 networks to attack this problem 02:48 this type of neural network is the most 02:50 commonly used deep learning architecture 02:52 in computer vision 02:54 the idea behind this deep neural network 02:56 architecture is to mimic the human's 02:58 visual system if you want to learn more 03:00 about the foundation of convolutional 03:02 neural networks 03:03 or cnns i will refer you to their video 03:05 on the top right corner on your screen 03:07 where i'm explaining them more in depth 03:11 they train their algorithm with real 03:13 images like this one 03:15 taken by drones and aircraft with 03:17 annotations made by the same 03:19 professionals that are usually 03:20 manually analyzing them this is a 03:23 challenging task even for deep learning 03:25 because of all the possible variations 03:27 in colors and sun reflections as you can 03:29 see here 03:31 in short their model is a regular binary 03:33 classifier 03:34 cnn architecture composed of 03:36 convolutions and poolings 03:38 terms that i explained in the video i 03:40 referenced earlier 03:41 that outputs a binary response telling 03:43 us if there are fmls or not in the 03:46 picture 03:46 the depth of the network is due to these 03:48 convolution layers 03:50 compressing the image and creating many 03:52 feature maps 03:53 which are the outputs of the filters 03:55 ending with a general representation 03:57 of the image allowing us to know in 03:59 general 04:00 what the image contains such as fml in 04:03 this case 04:04 note that this exact same architecture 04:06 could have been used on 04:08 any other computer vision application 04:10 with a test to classify whether or not 04:12 something is in the image such as 04:14 putting a defect on a manufacturer part 04:16 or telling if there is a dog or not what 04:18 they did differently making it powerful 04:20 to fml detection 04:22 is that they had the idea to split the 04:24 image into 25 smaller cells 04:26 that each outputs a classification 04:28 result fml 04:30 or not yielding much better overall 04:32 accuracy 04:33 then they used the shiny package of r 04:37 to develop their application their 04:39 algorithm allows the detection and 04:41 quantification 04:42 of fmls as well as providing support to 04:45 the monitoring and assessment of this 04:47 environmental threat 04:48 however it's still not completely 04:50 automated yet and requires a human in 04:52 the loop 04:53 as of now they are still looking for 04:55 more annotated data to allow their 04:57 algorithm to also 04:58 identify the size color and type of fml 05:01 which are very relevant information for 05:03 planning well-targeted policy and 05:05 mitigation measures 05:07 this is still an amazing application of 05:09 deep learning with a great use case that 05:11 will benefit everyone 05:13 of course this was just an introduction 05:15 to this new paper 05:16 and i linked both the paper their code 05:18 and their application 05:20 in the description below if you would 05:21 like to read more about it or even 05:23 try it out yourself please leave a like 05:26 if you went this far in the video 05:28 and since there are over 80 percent of 05:30 you guys that are not subscribed yet 05:32 please consider subscribing to the 05:33 channel to not miss any further news 05:36 thank you for watching 05:40 [Music]

Using AI to Detect and Count Plastic Waste in the Ocean

The so called progressive industrialisation has probably done more harm to our planet than good. Today, the world has found itself amidst the crisis of waste management, specifically plastic waste management. If we step back and look at the bigger picture by the numbers, the picture is much more ugly than we can even imagine. Source: sailorsforthesea.org They said diamond is forever, but hey! Plastic is forever too. We all know how severe the problem of waste management is, especially for the developing countries due to lack of resources. This is where kicks in. technology According to a recent study, 90 percent of plastic debris in the ocean , eight in Asia and two in Africa. comes from 10 rivers Let’s talk about solutions. There is enough plastic in this entire world that we could stop mining oil for a while and use the available trash to generate some energy. Yes, it is possible to generate energy out of plastic. _In the adventure classic Back to the Future, Emmett "Doc" Brown uses energy generated from rubbish to power his…_theconversation.com How we can turn plastic waste into green energy Fundamentally, plastic is made up of carbon and hydrogen, which is essentially what fossil fuels are made up of. According to the link above, plastics are among the most valuable waste materials — although with the way people discard them, you probably wouldn’t know it. It’s possible to convert all plastics directly into useful forms of energy and chemicals for industry, called using a process “cold plasma pyrolysis”. Apart from the above mentioned solutions, we all can contribute to the cause bit by bit. Here’s how. _Plastic Bank, igniting a Social Plastic® revolution. Uniting and enrolling humanity for local action that creates…_www.plasticbank.com Stop Ocean Plastic Let’s look at the example of . A company based in Indonesia whose aim is to reduce flow of plastic into the oceans. Any regular person can collect plastic waste from around their surrounding (for example, from their own house, or some factory nearby) and deposit the plastic in the plastic bank. In exchange, they can get money or energy or internet or some commodity. Plastic Bank blockchain The video below explains everything beautifully! There are so about a 100 more startups who strive to achieve the same results. Today, it is not at all tough to contribute to the noble cause. In fact, it is imperative to tackle the problem now or else all advancements the mankind is making in the field of technology would render futile because there won’t be a planet to live at all. Some may argue that Mars is ready for us, but to clear those doubts; we have to wait for a few more centuries to destroy Mars again. There is a beautiful documentary made by NatGeo which I saw last evening. It describes how far or near are we to make Mars our home. Here’s the link:

PLASTIQ

plastiq.com

51-200 employees

Since 2012

COMPANY RANKING

PLASTIQ

EVERGREEN INDEX #8489

Representing this company? Click here to claim and customize this page!

Plastiq WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

PLASTIQ

plastiq.com

51-200 employees

Since 2012

COMPANY RANKING

PLASTIQ

EVERGREEN INDEX #8489

RELATED COMPANIESRANK

STORIES ABOUT PLASTIQ

Representing this company? Click here to claim and customize this page!

Plastiq WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!