AI Essentials

Research

Discover how AI, Machine Learning and advanced algorithms impact our lives, our jobs and the economy thanks to expert articles that include discussion on the potential, limits and consequences of AI

AI Essentials

Top news of the week: 15.07.2021.

The Real World
Learning
Neuroscience
Policy
Enter key
Algorithm

Research

@jure shared
On Jul 9, 2021
RT @PeterWBattaglia: We’re looking for a Research Scientist on our Structured Intelligence team at DeepMind - especially with experience or interest in GNNs. See the link below to apply, or feel free to reach out to me directly. https://t.co/OLVrqYyiQw
Open
Research Scientist, Structured Intelligence

Research Scientist, Structured Intelligence

Careers at DeepMind

@AlisonBLowndes shared
On Jul 14, 2021
RT @nvidia: Now is a great time to build your career as a #developer or technologist. We've got an essential learning series in #AI, robotics, deep learning, and accelerated graphics to get you on your way. https://t.co/XpsKNf6bMc https://t.co/vOUEMDkBcT
Open
NVIDIA AI Essentials Learning Series

NVIDIA AI Essentials Learning Series

Kickstart your career in AI in this AI Learning Series.

@glouppe shared
On Jul 13, 2021
RT @EmtiyazKhan: Our new paper on "The Bayesian Learning Rule" is now on arXiv, where we provide a common learning-principle behind a variety of learning algorithms (optimization, deep learning, and graphical models). https://t.co/Kta3EGvWba Guess what, the principle is Bayesian. A very long🧵 https://t.co/QI0FhUyGH8
Open
The Bayesian Learning Rule

The Bayesian Learning Rule

We show that many machine-learning algorithms are specific instances of a single algorithm called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide-range ...

@ericjang11 shared
On Jul 14, 2021
RT @EugeneVinitsky: Are off-policy methods more sample efficient than on-policy in MARL? We show that PPO + centralized value functions is a strong baseline on a variety of cooperative MARL tasks! Paper: https://t.co/XtpEayB7cn Blog post: https://t.co/KDiBx51XdR https://t.co/jnNa7rgq88
Open
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games

The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games

The BAIR Blog

@syhw shared
On Jul 13, 2021
RT @YugeTen: Paper + Code release! We propose Fish🐟, an effective algorithm for domain generalisation. It learns invariant features by maximising gradient inner product across domains. 📜:https://t.co/lwvzym2REu 👩‍💻:https://t.co/4tf7VaWK8y Work done during internship at FAIR with @syhw. 🧵 https://t.co/BO6zhd6ocd
Open
Gradient Matching for Domain Generalization

Gradient Matching for Domain Generalization

Machine learning systems typically assume that the distributions of training and test sets match closely. However, a critical requirement of such systems in the real world is their ability ...

@_rockt shared
On Jul 9, 2021
RT @marwinsegler: If you want to persue a PhD in Machine Learning at UCL @ai_ucl with Prof. Brooks Paige - have a look at this opportunity! I'll be also involved - feel free to reach out! https://t.co/YgfA2wQmWV
Open
Machine learning algorithms for automated decision making under domain shift

Machine learning algorithms for automated decision making under domain shift

PhD Project - Machine learning algorithms for automated decision making under domain shift at University College London, listed on FindAPhD.com

@jeremyphoward shared
On Jul 14, 2021
RT @iScienceLuvr: A new blog post! Coding with GitHub Copilot - My thoughts and experience on the new GitHub Copilot tool. https://t.co/8rhYGYTvXD Here's a quick summary thread👇
Open
Coding with GitHub Copilot

Coding with GitHub Copilot

My thoughts and experience on the new GitHub Copilot tool.

@ryan_p_adams shared
On Jul 14, 2021
RT @its_dibya: Fresh on ArXiv! https://t.co/KY9tnogl6Z TL;DR: Standard RL algos are sub-optimal for generalization. Why? When generalizing from limited training scenarios,the fully-observed env implicitly becomes partially-observed, necessitating new algos and policies to generalize well (1/n) https://t.co/BTL768Dwox
Open
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Generalization is a central challenge for the deployment of reinforcement learning (RL) systems in the real world. In this paper, we show that the sequential structure of the RL problem ...

Read more: Research
weekly 15.07.2021
View archives
Back to home

Subscribe to AI Essentials - Research.

Avoid an information overload and get the most trusted industry news hand-picked by the top Experts. Sign up for the weekly AI Essentials - Research.
Privacy Policy

Sign up for the weekly AI Essentials - Research newsletter

Never again miss anything or anyone that matter in AI Essentials

Sign up and receive the AI Essentials - Research weekly email newsletter directly to your inbox. Make more informed business decisions based on insight for the most trusted industry experts, faster.
Privacy Policy