teal background with hexagon 3d shape

Microsoft Research
AI for Science

新闻与深度文章

新闻报道 | Metaverse Post

Microsoft recently launched DeepSpeed4Science initiative to apply deep learning in natural sciences, including drug development and renewable energy. DeepSpeed, an open-source AI framework, aims to accelerate and scale up deep learning processes.

新闻报道 | WinBuzzer

Microsoft has introduced the DeepSpeed4Science initiative through its DeepSpeed team. The initiative focuses on the application of deep learning in the natural sciences, targeting areas such as drug development and renewable energy. The DeepSpeed system, an open-source AI framework from…

DeepSpeed4Science Initiative - graphic with 6 icons
微软研究院博客

| Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang, Conglong Li, Martin Cai, 和 Yuxiong He

Editor’s note, Sept. 28, 2023 – The founding collaborators list was updated to correct omissions and the scientific foundation model graph was updated to correct information. In the next decade, deep learning may revolutionize the natural sciences, enhancing our capacity to…

A schematic diagram illustrating the goal of Distributional Graphormer (DiG). A molecular system is represented by a basic descriptor D, such as the amino acid sequence for a protein. DiG transforms D into a structural ensemble S, which consists of multiple possible conformations and their probabilities. S is expected to follow the equilibrium distribution of the molecular system. A legend shows a example of D and S for Adenylate kinase protein.
微软研究院博客

| Shuxin Zheng, Chang Liu, Yu Shi, Ziheng Lu, Fusong Ju, Jianwei Zhu, Hongxia Hao, Peiran Jin, Frank Noé, Haiguang Liu, 和 Tie-Yan Liu

Distributional Graphormer, Microsoft’s new deep learning framework for predicting the equilibrium distribution of molecular structures, can generate realistic and diverse molecular structures with high efficiency and low cost.

Doctor at computer

新闻报道 | Microsoft News Centre UK

The National Health Service at Addenbrooke’s Hospital in Cambridge is now able to plan radiotherapy treatments faster than in the past, thanks to AI advances that are cutting wait times. As the NHS approaches its 75th birthday, it continues to…

文章

We are open sourcing CliffordLayers (opens in new tab), a repo for building neural network layers inspired by Clifford / Geometric Algebras. This repo contains the source code of our ICLR 2023 paper Clifford Neural Layers for PDE Modeling (opens…

新闻报道 | Autonomous Systems and Robotics Group Article

We are announcing ClimaX, a flexible and generalizable deep learning model for weather and climate science. ClimaX is trained using several heterogeneous datasets spanning many weather variables at multiple spatio-temporal resolutions. We show that such a foundational model can be…

新闻报道 | Autonomous Systems and Robotics Group Article

We are open sourcing PDEArena, a modern, scalable, and easy to use PDE surrogate benchmarking framework. PDEArena is designed to train and evaluate neural surrogates for partial differential equations (PDE) at scale. As such, PDEArena contains state of the art…

新闻报道 | Tagesspiegel Background Digitalisierung und AI

Im Rahmen des Microsoft-Forschungsprogramms „AI4Science“ arbeitet ein globales Team an Standorten in Europa, Asien und den USA an der Frage, was Methoden des maschinellen Lernens zur Lösung naturwissenschaftlicher Probleme beitragen können. Seit Anfang Oktober gibt es auch in Berlin ein Lab. Geleitet…