Dr. Debadeepta Dey is a Principal Researcher in the Adaptive Systems and Interaction group at MSR and he’s currently exploring several lines of research that may help bridge the gap between perception and planning for autonomous agents, teaching them make decisions under uncertainty and even to stop and ask for directions when they get lost!
On today’s podcast, Dr. Dey talks about how his latest work in meta-reasoning helps improve modular system pipelines and how imitation learning hits the ML sweet spot between supervised and reinforcement learning. He also explains how neural architecture search helps enlighten the “dark arts” of neural network training and reveals how boredom, an old robot and a several “book runs” between India and the US led to a rewarding career in research.
https://www.microsoft.com/research

108 - Neural architecture search, imitation learning and other ML “defense against the dark arts” techniques with Dr. Debadeepta Dey

An ongoing series of conversations bringing you right up to the cutting edge of Microsoft Research.

Technology

Tech News

Podcasting

Gadgets

Software How-To

Behind every emerging technology is a great idea propelling it forward. In the new Microsoft Research Podcast series, Ideas, members of the research community at Microsoft discuss the beliefs that animate their research, the experiences and thinkers that inform it, and the positive human impact it targets.  In this episode, host Gretchen Huizinga talks with Distinguished Scientist and Lab Director Abigail Sellen (https://www.microsoft.com/en-us/research/people/asellen/). The idea that computers could be designed for people is commonplace today, but when Sellen was pursuing an advanced degree in psychology, it was a novel one that set her on course for a career in human-centric computing. Today, Sellen and the teams she oversees are studying how AI could—and should—be designed for people, focusing on helping to ensure new developments support people in growing the skills and qualities they value. Sellen explores those efforts through the AI, Cognition, and the Economy initiative—or AICE, for short—a collective of interdisciplinary scientists examining the short- and long-term effects of generative AI on human cognition, organizational structures, and the economy.Learn more:AI, Cognition, and the Economy (AICE) (https://www.microsoft.com/en-us/research/collaboration/ai-cognition-and-the-economy-aice/) Responsible AI Principles and Approach | Microsoft AI (https://www.microsoft.com/en-us/ai/principles-and-approach/)  The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond (https://www.microsoft.com/en-us/research/publication/the-rise-of-the-ai-co-pilot-lessons-for-design-from-aviation-and-beyond/) The Myth of the Paperless Office (https://www.microsoft.com/en-us/research/publication/myth-paperless-office/)

Ideas: Designing AI for people with Abigail Sellen

Members of the research community at Microsoft work continuously to advance their respective fields. Abstracts brings its audience to the cutting edge with them through short, compelling conversations about new and noteworthy achievements. In this episode, Principal Research Manager Andrey Kolobov (https://www.microsoft.com/en-us/research/people/akolobov/) joins host Gretchen Huizinga to discuss “WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle (https://www.microsoft.com/en-us/research/publication/windseer-real-time-volumetric-wind-prediction-over-complex-terrain-aboard-a-small-uav/),” or sUAV. sUAVs can fly farther and more safely if they can reason about the terrain-affected wind in their vicinity. Traditional wind predictions ignore small-terrain features and work at the scale of hours and miles, far too coarsely for sUAVs. WindSeer can estimate the terrain-dependent wind field around an sUAV in flight, with limited onboard compute and measurement data, paving the way for safer and more energy-efficient autonomous drone operation.Learn more:WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle (https://www.microsoft.com/en-us/research/publication/windseer-real-time-volumetric-wind-prediction-over-complex-terrain-aboard-a-small-uav/)

Abstracts: May 20, 2024

In the Microsoft Research Podcast series What’s Your Story, Johannes Gehrke explores the who behind the technical and scientific advancements helping to reshape the world. A systems expert whose 10 years with Microsoft spans research and product, Gehrke talks to members of the company’s research community about what motivates their work and how they got where they are today.In this episode, Gehrke is joined by Jacki O’Neill (https://www.microsoft.com/en-us/research/people/jaoneil/), director of Microsoft Research Africa, Nairobi (formerly the Microsoft Africa Research Institute, or MARI) in Kenya. O’Neill pitched the idea for the lab after seeing an opportunity to expand the Microsoft research portfolio. She shares how a desire to build tech that can have global societal impact and a familial connection to the continent factored into the decision; how a belief that life is meant to be exciting has allowed her to take big personal and professional swings; and how her team in Nairobi is applying their respective expertise in human-computer interaction, machine learning, and data science to pursue globally equitable AI.To learn more about the global impact of AI, efforts to make AI more equitable, and related topics, register for Microsoft Research Forum (https://researchforum.microsoft.com/), a series of panel discussions and lightning talks around science and technology research in the era of general AI.Learn more:* Jacki O'Neill at Microsoft Research (https://www.microsoft.com/en-us/research/people/jaoneil/?msockid=23b9b9353d686c6e3047ad083c866df5)* Microsoft Research Africa (formerly MARI) (https://www.microsoft.com/en-us/research/group/microsoft-africa-research-institute-mari/)

What’s Your Story: Jacki O’Neill

Members of the research community at Microsoft work continuously to advance their respective fields. Abstracts brings its audience to the cutting edge with them through short, compelling conversations about new and noteworthy achievements.In this episode, Senior Principal Researcher Michel Galley (https://www.microsoft.com/en-us/research/people/mgalley/) joins host Gretchen Huizinga to discuss “MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts (https://www.microsoft.com/en-us/research/publication/mathvista-evaluating-mathematical-reasoning-of-foundation-models-in-visual-contexts/),” which was accepted at the 2024 International Conference on Learning Representations (ICLR). MathVista, an open-source benchmark, combines new and existing data to measure how good models are at solving a variety of math problems that involve processing images as well as text, helping to gain insight into their reasoning capabilities.Read the paperGet the code & dataset

Abstracts: May 6, 2024

Behind every emerging technology is a great idea propelling it forward. In the new Microsoft Research Podcast series, Ideas, members of the research community at Microsoft discuss the beliefs that animate their research, the experiences and thinkers that inform it, and the positive human impact it targets. In this episode, host Gretchen Huizinga talks with Rafah Hosn, partner group product manager for AI Frontiers at Microsoft Research. Hosn’s professional experience spans the gamut—from research to product to engineering to research again, the discipline’s uniquely high levels of creativity, curiosity, and intellect drawing her back in. Energized by past technical disruptions she’s experienced, Hosn is on what she describes as her “most exciting adventure” yet, helping to drive scientific advancement in AI and to answer a big question: how far can we push machine intelligence while still delivering technologies people can derive value from? Learn more:* AI Frontiers - Microsoft Research (https://www.microsoft.com/en-us/research/lab/ai-frontiers/)* Responsible AI Principles and Approach | Microsoft AI (https://www.microsoft.com/en-us/ai/principles-and-approach/)

108 - Neural architecture search, imitation learning and other ML “defense against the dark arts” techniques with Dr. Debadeepta Dey

Download our free app to listen on your phone