Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
Less pain, more gain: A simple method for VAE training with less of that KL-vanishing agony
There is a growing interest in exploring the use of variational auto-encoders (VAE), a deep latent variable model, for text generation. Compared to the standard RNN-based language model that generates sentences one word at a…
Video
Re-engineering Brain-Machine Interfaces to Optimize Control and Learning
Direct interfaces with the brain provide exciting new ways to restore and repair neurological function. For instance, motor Brain-Machine Interfaces (BMIs) can bypass a paralyzed person’s injury by repurpose intact portions of their brain to…
Podcast
Holograms, spatial anchors and the future of computer vision with Dr. Marc Pollefeys
Episode 71, April 10, 2019 – On today’s podcast, Dr. Pollefeys brings us up to speed on the latest in computer vision research, including his innovative work with Azure Spatial Anchors, tells us how devices…
Video
How does Batch Normalization Help Optimization?
Batch normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks. However, despite its pervasiveness, the exact reasons for BatchNorm’s effectiveness are still poorly understood. In this…
Publication