Algorithmic foundations of neural architecture search
Neural architecture search (NAS)—the problem of selecting which neural model to use for your learning problem—is a promising direction for automating and democratizing machine learning. Early NAS methods achieved impressive results on canonical image classification…
Urban Futures – Summer Workshop
The Microsoft Urban Futures Summer Workshop will be three intensive days of talks, discussion and planning for data driven urban transformation. At this event we will build a research driven coalition of civic, academic and…
Directions in ML: AutoML and Automating Algorithms
Join us as we bring together AutoML research communities from across the world to learn from each other and building on the latest knowledge and exploration. This speaker series features talks by outstanding academics and…
Domain-Adaptive Neural Automated Essay Scoring.
GLUECoS
This is the repo for the ACL 2020 paper GLUECoS: An Evaluation Benchmark for Code-Switched NLP GLUECoS is a benchmark comprising of multiple code-mixed tasks across 2 language pairs (En-Es and En-Hi)
DeepSpeed
DeepSpeed, part of the Microsoft AI at Scale initiative, is a deep learning optimization library that makes distributed training easy, efficient, and effective.