Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Publication
Dropout as a Regularizer of Interaction Effects
Publication
Universal Search and Recommendation
Microsoft Research Blog
First ever Microsoft Research Summit explores science and technology aimed at big challenges
For 30 years, Microsoft Research has brought together great minds from around the world to take on the biggest research challenges facing society. As we enter our fourth decade, the need for collaborative research—and the…
Publication
RKHS-SHAP: Shapley Values for Kernel Methods
Publication
Invariant Language Modeling
Tool
Machine Intelligence PyTorch Module Zoo
A number of PyTorch modules (neural network components) that are broadly (re)usable. The goal of this release is to provide a library to machine learning researchers to use and advance the state-of-the-art in the area.
Tool
Stochastic Mixture-of-Experts
This PyTorch package implements Taming Sparsely Activated Transformer with Stochastic Experts.
Tool
Meta Self-training for Few-shot Neural Sequence Labeling [Code]
This is the implementation of the paper Meta Self-training for Few-shot Neural Sequence Labeling. MetaST is short for meta-learning for self-training.