PhD Defense: Towards Human-AI Cooperation on Sequential Decision Making Problems
Shi Feng
Remote
Friday, July 16, 2021, 10:00 am-12:00 pm 
Abstract
The tools we use have a great impact on our productivity. It is imperative that tools are designed with the user's objectives in mind. From self-driving cars to tackling misinformation, from machine translation to breast cancer diagnosis, we are relying more and more on tools with artificial intelligence powered by machine learning models.
This thesis focuses on developing machine learning models that are maximally useful to humans. Our primary goal is to improve the productivity of human-AI cooperation on important decision making problems by understanding how human and AI interact. In the traditional approach to machine learning, humans are treated as either rivals or teachers. However, machine learning can make up for some of the shortcomings of humans. Treating humans as collaborators opens up several new directions of research.
In the first part of the thesis, we use flashcard learning as a testbed and study how human productivity can benefit from consuming information generated by machine learning models.
In the second part, we consider humans as decision makers, and investigate how explanations of machine learning predictions can improve the performance of human-AI teams on sequential decision making problems.
Finally, we study the limitations of natural language explanations for model predictions, as well as novel methods to improve them.
Examining Committee:
This thesis focuses on developing machine learning models that are maximally useful to humans. Our primary goal is to improve the productivity of human-AI cooperation on important decision making problems by understanding how human and AI interact. In the traditional approach to machine learning, humans are treated as either rivals or teachers. However, machine learning can make up for some of the shortcomings of humans. Treating humans as collaborators opens up several new directions of research.
In the first part of the thesis, we use flashcard learning as a testbed and study how human productivity can benefit from consuming information generated by machine learning models.
In the second part, we consider humans as decision makers, and investigate how explanations of machine learning predictions can improve the performance of human-AI teams on sequential decision making problems.
Finally, we study the limitations of natural language explanations for model predictions, as well as novel methods to improve them.
Examining Committee:
Chair: Dr. Jordan Boyd-Graber
Dean's rep: Dr. Eun Kyoung Choe
Members: Dr. Hal Daumé III
Dr. Marine Carpuat
Dean's rep: Dr. Eun Kyoung Choe
Members: Dr. Hal Daumé III
Dr. Marine Carpuat
Dr. John P. Dickerson
Dr. Alexander Rush
Dr. Alexander Rush
Bio
Shi Feng is a PhD candidate in Computer Science at University of Maryland. He is interested in human-AI cooperation: how machine learning can help humans make better decisions, and how humans can provide supervision more effectively. His past work focuses on natural language processing, and covers topics including interpretability, adversarial attacks, robustness, and human-in-the-loop evaluations. The overarching goal of his research is to build AI systems to augment human capabilities.
This talk is organized by Tom Hurst