Research
Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
This implements F# for Jupyter notebooks. View the Feature Notebook for some of the features that are included.
A programming language for designing and simulating computational devices made of DNA. The language uses DNA strand displacement as the main computational mechanism, which allows devices to be designed solely in terms of nucleic acids.…
We introduce such a programming language, which allows logical interactions between potentially undetermined proteins and genes to be expressed in a modular manner. Programs can be translated by a compiler into sequences of biological parts,…
InterpretML is an open-source python package for training interpretable models and explaining blackbox systems. Historically, the most intelligible models were not very accurate, and the most accurate models were not intelligible. Microsoft Research has developed…
Multi-task learning toolkit for natural language understanding, including knowledge distillation.
A Python package of accelerated first-order algorithms for solving relatively-smooth convex optimization problems. It implements all algorithms described in our recent paper on accelerated Bregman proximal gradient methods, including the baseline algorithms for comparison. It…
DiCE is a Python library to explain an ML model such that the explanation is truthful to the model and yet interpretable to people. This connects to the “Explainable AI systems” theme.
This repository hosts samples that demonstrate how to use Trill, a high-performance one-pass in-memory streaming analytics engine from Microsoft Research. It can handle both real-time and offline data, and is based on a temporal data…
Our objective is to develop a library of efficient machine learning algorithms that can run on severely resource-constrained edge and endpoint IoT devices ranging from the Arduino to the Raspberry Pi. Please see our GitHub (opens in new…