Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Project
Privacy Preserving Image Queries for Camera Localization
In this project, we have developed a new 6-DoF camera localization technique that conceals the content of the query image when localization is performed in a cloud-based service. In this way, we enhance the user's…
Video
Learning to Map Natural Language to General Purpose Source Code
Models that map natural language (NL) to source code in general purpose languages such as Java, Python, and SQL find utility amongst two main audiences viz. developers who can manipulate the generated code, and non-expert…
Microsoft Research Blog
Efficient inference for dynamical models using variational autoencoders
Dynamical systems theory provides a mathematical framework for studying how complex systems evolve over time, such as the neurons in our brains, the global climate system, or engineered cells. But predicting how these systems will…
Tool
Generative Neural Visual Artist (GeNeVA) – Training and Evaluation Code
Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction (opens in new tab).
Tool
Petridish: Efficient Forward Neural Architecture Search [0.1]
Petridish, is a neural architecture search (NAS) algorithm which iteratively adds shortcut connections to existing network layers. The added shortcut connections effectively perform gradient boosting on the augmented layers. The proposed algorithm is motivated by…
Publication