Sharing some of the latest research, announcements, and resources on deep learning. By Isaac Madan ( email ) Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: , , , , , , , , , , ( , , and the of 20+ resources we outlined in April 2016. As always, this list is not comprehensive, so if there’s something we should add, or if you’re interested in discussing this area further. July June ( part 1 , part 2 , part 3 , part 4 ) May April ( part 1 , part 2 ) March part 1 February November September part 2 & October part 1 September part 1 August ( part 1 , part 2 ) July part 1 part 2 ), June original set let us know Professional-quality photo post-processed by AI. Research & Announcements by Rajpurkar et al of Stanford ML. Original paper . Cardiologist-Level Arrhythmia Detection With Convolutional Neural Networks We develop a model which can diagnose irregular heart rhythms, also known as arrhythmias, from single-lead ECG signals better than a cardiologist. Key to exceeding expert performance is a deep convolutional network which can map a sequence of ECG samples to a sequence of arrhythmia annotations along with a novel dataset two orders of magnitude larger than previous datasets of its kind. here by Hui Wang of Google Research. Original paper . Using Deep Learning to Create Professional-Level Photographs Whether a photograph is beautiful or not is measured by its aesthetic value, which is a highly subjective concept. To explore how ML can learn subjective concepts, we introduce an experimental deep-learning system for artistic content creation. It mimics the workflow of a professional photographer, roaming landscape panoramas from Google Street View and searching for the best composition, then carrying out various postprocessing operations to create an aesthetically pleasing image. here by Suwajanakorn of University of Washington. Original paper . How to turn audio clips into realistic lip-synced video et al Given audio of President Barack Obama, we synthesize a high quality video of him speaking with accurate lip sync, composited into a target video clip. here by Benoît Rostykus of Netflix. A lightweight neural network library for sparse data. Introducing Vectorflow A subset of our problems [at Netflix] involve dealing with extremely sparse data; the total dimensionality of the problem at hand can easily reach tens of millions of features, even though every observation may only have a handful of non-zero entries. For these cases, we felt the need for a minimalist library that is specifically optimized for training shallow feedforward neural nets on sparse data in a single-machine, multi-core environment. by OpenAI. Dota 2 bot We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. by Peiyun Hu and Deva Ramanan of Carnegie Mellon. Original paper . Finding Tiny Faces We develop a face detector (Tiny Face Detector) that can find ~800 faces out of ~1000 reportedly present, by making use of novel characterization of scale, resolution, and context to find small objects. GitHub repo includes MATLAB implementation of Tiny face detector, including both training and testing code. A demo script is also provided. here Credit: https://xkcd.com/1838/ Resources, Tutorials & Data by Andrew Ng**.** deeplearning.ai: Announcing new Deep Learning courses on Coursera I have been working on three new AI projects, and am thrilled to announce the first one: deeplearning.ai , a project dedicated to disseminating AI knowledge, is launching a new sequence of Deep Learning courses on Coursera. These courses will help you master Deep Learning, apply it effectively, and build a career in AI. by Google. Visualization tools to better explore & understand machine learning data sets. Facets The power of machine learning comes from its ability to learn patterns from large amounts of data. Understanding your data is critical to building a powerful machine learning system. Facets contains two robust visualizations to aid in understanding and analyzing machine learning datasets. by Luong . TensorFlow Neural Machine Translation Tutorial et al This tutorial gives readers a full understanding of seq2seq models and shows how to build a competitive seq2seq model from scratch. We focus on the task of Neural Machine Translation (NMT) which was the very first testbed for seq2seq models with wild success. by Francois Chollet. The limitations of deep learning The only real success of deep learning so far has been the ability to map space X to space Y using a continuous geometric transform, given large amounts of human-annotated data. Doing this well is a game-changer for essentially every industry, but it is still a very long way from human-level AI. by Slav Ivanov. Insights and tips based on experience into why a network may not be training. 37 Reasons why your Neural Network is not working by fast.ai. 7 week course on deep learning spanning artistic style, generative models, memory networks, attentional models, neural translation, and segmentation. Part 1, , is . Cutting Edge Deep Learning For Coders, Part 2 Practical Deep Learning for Coders here by Andrew Ng. Andrew Ng interviews Geoffrey Hinton, of University of Toronto and Google. 40 min video. Heroes of Deep Learning by Jovan Sardinha. An introduction to model ensembling Model ensembling represents a family of techniques that help reduce generalization error in machine learning tasks. In this article, I will share some ways that ensembling has been employed and some basic intuition on why it works. by Alex Honchar. Tutorial on financial forecasting via artificial neural networks. Neural networks for algorithmic trading: Multimodal and multitask deep learning by Sasank Chilamkurthy of Qure. Literature review and overview of semantic segmentation, i.e. understanding an image at a pixel level. A 2017 Guide to Semantic Segmentation with Deep Learning By . Isaac is an investor at Venrock ( ). If you’re interested in deep learning or there are resources I should share in a future newsletter, I’d love to hear from you. Isaac Madan email is a newsletter of entrepreneurial ideas & perspectives by investors, operators, and influencers. Requests for Startups ** **❤” Please tap or click “︎ to help to promote this piece to others.
