If you enjoy the newsletter, please consider sharing it on Twitter, Facebook, etc! Really appreciate
|
|
September 18 · Issue #61 · View online
The Wild Week in AI is a weekly AI & Deep Learning newsletter curated by @.
|
|
If you enjoy the newsletter, please consider sharing it on Twitter, Facebook, etc! Really appreciate the support :)
|
|
Because, Neural networks. Image credit goes to @keunwoochoi
|
|
Geoffrey Hinton is suspicious of back-propagation
Back-propagation is the method by which almost all neural networks are trained today. In a recent interview, Hinton, one of the fathers of Deep Learning, mentioned that he would “throw it all away and start again”. To push materially ahead, entirely new methods will probably have to be invented.
|
Facebook AI Research expands to Montreal
As part of Facebook AI Research (FAIR), this new team will join more than 100 scientists across Menlo Park, New York, and Paris in working to advance the field of artificial intelligence. The Montreal lab will house research scientists and engineers working on a wide range of AI research projects, but it will also have a special focus on reinforcement learning and dialog systems.
|
Sophia Genetics raises $30 million to help doctors diagnose using AI and genomic data
Sophia Genetics, a big data analytics company that’s using AI to help medical professionals diagnose and treat patients through genomic analysis, has raised $30 million in a round of funding led by Balderton Capital, with participation from 360 Capital Partners, Invoke Capital, and Alychlo.
|
|
Learning to Model Other Minds (OpenAI)
An algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma.
|
AI Gym Workout
An easy-to-understand introduction to Proximal Policy Optimization (PPO) and extensions to solve MuJoCo and RoboSchool environments. All code is on Github.
|
Learning to Optimize with Reinforcement Learning
The algorithms that power machine learning are still designed manually. This raises a natural question: can we learn these algorithms instead?
|
|
Custom Visualizations with the TensorBoard API
To allow the creation of new and useful visualizations, Google announced the release of a set of APIs that allows developers to add custom visualization plugins to TensorBoard.
|
Dilated Residual Network implementations
|
Introduction to TensorFlow Datasets and Estimators
TensorFlow 1.3 introduces two important features: Datasets and Estimators. This post shows how they fit in the TensorFlow architecture.
|
Goodbooks 10k: Ten thousand books, six million ratings
This dataset contains six million ratings for ten thousand most popular (with the most ratings) books from goodreads.com.
|
|
[1709.02840] A Brief Introduction to Machine Learning for Engineers
A “brief” 200-page introduction. This work aims at providing an introduction to key concepts, algorithms, and theoretical frameworks in machine learning, including supervised and unsupervised learning, statistical learning theory, probabilistic graphical models and approximate inference.
|
[1709.03856] StarSpace: Embed All The Things!
A general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification, ranking tasks such as information retrieval/web search, collaborative filtering-based or content-based recommendation, embedding of multi-relational graphs, and learning word, sentence or document level embeddings. In each case the model works by embedding those entities comprised of discrete features and comparing them against each other – learning similarities dependent on the task.
|
[1706.05374] Expected Policy Gradients
Expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected SARSA, EPG integrates across the action when estimating the gradient, instead of relying only on the action in the sampled trajectory.
|
|
AI Hype? NIPS registration timeline until conference is sold out. Credit to @lxbrun.
|
Did you enjoy this issue?
|
|
|
|
If you don't want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
|
|
|