What do pruned deep neural networks forget?

Official cleanlab repo is at https://github.com/cleanlab/cleanlab - cgnorthcutt/cleanlab

PyTorch code for our paper: Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers? https://arxiv.org/abs/1908.09625 - Mrtn...

NeurIPS 2019: Learn to Move - Walk Around, 2nd place solution - GitHub - Scitator/run-skeleton-run-in-3d: NeurIPS 2019: Learn to Move - Walk Around, 2nd place solution

How to tune and optimize Prophet using domain knowledge to add greater control to your forecasts.

Posted by Florian Kainz and Kiran Murthy, Software Engineers, Google Research Taking pictures of outdoor scenes at night has so far been the dom...

Learn how we enable AR effects to fully interact with a scene geometry, for example, to enable occlusions by real objects in the scene.

Neural Graph Differential Equations (Neural GDEs). Contribute to Zymrael/gde development by creating an account on GitHub.

Most of us last saw calculus in school, but derivatives are a critical part of machine learning, particularly deep neural networks, which are trained by optimizing a loss function. This article is an attempt to explain all the matrix calculus you need in…

Our radar perception pipeline delivers 360-degree surround perception around the vehicle, using production-grade radar sensors operating at the 77GHz automotive microwave band.

gnn explainer. Contribute to RexYing/gnn-model-explainer development by creating an account on GitHub.

Jerome Pesenti is encouraged by progress in artificial intelligence, but sees the limits of the current approach to deep learning.

Machine learning algorithms are typically evaluated using resampling techniques such as k-fold cross-validation. During the k-fold cross-validation process, predictions are made on test sets comprised of data not used to train the model. These predictions…

To advance research on AI that can understand others’ points of view and collaborate effectively, Facebook AI has developed a bot that sets a new state of the art in Hanabi, a card game in which all players work together.

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors - mhagiwara/github-typo-corpus

AI Researcher at the Samsung SAIT AI Lab 🐱‍💻

Facebook AI Managing Director Joelle Pineau discusses the importance of reproducibility in AI research, and shares early results from the first reproducibility challenge at NeurIPS 2019.

Text to speech (TTS) has attracted a lot of attention recently due to advancements in deep learning. Neural network-based TTS models (such as Tacotron 2, DeepVoice 3 and Transformer TTS) have outperformed conventional concatenative and statistical parametric…

As part of the fastMRI research project to use AI to speed up MRI scans, NYU Langone Health is making a new dataset of de-identified brain MRIs available to researchers and Facebook AI is sharing additional tools and resources.