Fairness in Machine Learning
Machine learning is increasingly being adopted by various domains: governments, credit, recruiting, advertising, and many others. Fairness and equality are critical aspects, especially in light of anti-discriminatory laws in these domains. Opaque machine learning models:…
Researchers develop new visual intelligence techniques to boost smart home security
By Kangping Liu, Senior Research Program Manager, Microsoft Research Asia Imagine when you leave your house or apartment that a smart home security system can automatically “look after” your home, giving you real-time notices about…
Computational Pragmatics
Defining pragmatics has not been easy. We discuss the major themes that have been dealt with in the field: The macro perspective: Speech Act Theory The micro perspective: Cooperative Principles and Implicature Merging the macro…
Divide and conquer: How Microsoft researchers used AI to master Ms. Pac-Man
Microsoft researchers have created an artificial intelligence-based system that learned how to get the maximum score on the addictive 1980s video game Ms. Pac-Man, using a divide-and-conquer method that could have broad implications for teaching…
Hybrid Reward Architecture (HRA) Achieving super-human performance on Ms. Pac-Man
Games are popular as a test-bed for new machine learning techniques because they can be very challenging and allow for easy analysis of new learning techniques in a controlled environment. For reinforcement learning, where the…