Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
ReDial: Recommendation dialogs for bridging the gap between chit-chat and goal-oriented chatbots
Chatbots come in many flavors, but most can be placed in one of two categories: goal-oriented chatbots and chit-chat chatbots. Goal-oriented chatbots behave like a natural language interface for function calls, where the chatbot asks…
Microsoft Research Blog
Discovering the best neural architectures in the continuous space
If you’re a deep learning practitioner, you may find yourself faced with the same critical question on a regular basis: Which neural network architecture should I choose for my current task? The decision depends on…
Video
Discover[i]: Component-based Parameterized Reasoning for Distributed Applications
Distributed systems are hard to get right. There have been many notable efforts in formal reasoning for distributed systems: these efforts have focused on language design, automated or semi-automated verification, and, more recently, on automated…
![Video: Discover[i]: Component-based Parameterized Reasoning for Distributed Applications](https://cm-edgetun.pages.dev/en-us/research/wp-content/uploads/2018/11/42373_Discoveri-Component-based-Parameterized-Reasoning_video_10_2019_1280x720-1024x576.jpg)
Video
Machine Teaching Overview
Microsoft Research AI shares how machine teaching can revolutionize the way we interact with machines in our daily lives. Humankind’s rich diversity is an insurmountable challenge for traditional machine learning. It’s simply not feasible to…
Microsoft Research Blog
Minimizing trial and error in the drug discovery process
In 1928, Alexander Fleming accidentally let his petri dishes go moldy, a mistake that would lead to the breakthrough discovery of penicillin and save the lives of countless people. From these haphazard beginnings, the pharmaceutical…
Podcast
Machine learning and the learning machine with Dr. Christopher Bishop
Episode 52, November 28, 2018 – Dr. Christopher Bishop talks about the past, present and future of AI research, explains the No Free Lunch Theorem, talks about the modern view of machine learning (or how…
Project
AutoML
State-of-the-art machine learning/AI systems consist of complex pipelines with choices of hyperparameters, models and configuration details that need to be tuned for optimal performance. The AutoML project develops automated methods for optimizing AI pipelines, making…
Video
Delayed Impact of Fair Machine Learning
Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventional wisdom suggests that fairness criteria promote the long-term well-being of those…
