A collection of infrastructure and tools for research in neural network interpretability. - tensorflow/lucid

We’re open-sourcing a new platform for experimenting with reinforcement learning to proactively adapt to changing traffic patterns.

A guest post by Sandeep Mistry & Dominic Pajak of the Arduino team

We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic…

Deep recommender models using PyTorch. Contribute to maciejkula/spotlight development by creating an account on GitHub.

Facebook AI is open-sourcing ReAgent, the most comprehensive and modular open source platform for creating AI-based reasoning systems, and the first to include policy evaluation to incorporate offline feedback.

In this tutorial you are going to learn about the Naive Bayes algorithm including how it works and how to implement it from scratch in Python (without libraries). We can use probability to make predictions in machine learning. Perhaps the most widely used…

Our Transformers library implements several state-of-the-art transformer architectures used for NLP tasks like text classification…

NeurIPS 2019 Workshop

Posted by Kevin Kilgour, Software Engineer and Thomas Unterthiner, Research Software Engineer, Google Research, Zürich "I often say that when you...

The Deepfake Detection Challenge is adding new partners, including Amazon Web Services, and also sharing an initial dataset of videos.

Posted by Alexander B Wiltschko, Senior Research Scientist, Google Research Smell is a sense shared by an incredible range of living organisms, a...

Linear regression is a classical model for predicting a numerical quantity. The parameters of a linear regression model can be estimated using a least squares procedure or by a maximum likelihood estimation procedure. Maximum likelihood estimation is a probabilistic…

Posted by Daniel Smilkov, Sandeep Gupta, and Vishy Tirumalashetty

Contribute to flowersteam/teachDeepRL development by creating an account on GitHub.

Meta-reinforcement learning algorithms can enable robots to acquire new
skills much more quickly, by leveraging prior experience to learn how to learn.
However, much of the current research on...