Towards Human-AI Cooperation on Sequential Decision Making Problems

Simple item page
dc.contributor.advisorBoyd-Graber, Jordanen_US
dc.contributor.authorFeng, Shien_US
dc.contributor.departmentComputer Scienceen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2022-02-04T06:30:53Z
dc.date.available2022-02-04T06:30:53Z
dc.date.issued2021en_US
dc.description.abstractThe 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 (AI) 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 passively consuming information generated by machine learning models. In the second part, we consider humans as active 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.en_US
dc.identifierhttps://doi.org/10.13016/a6uh-ni8o
dc.identifier.urihttp://hdl.handle.net/1903/28398
dc.language.isoenen_US
dc.subject.pqcontrolledArtificial intelligenceen_US
dc.subject.pquncontrolledHuman-AI cooperationen_US
dc.subject.pquncontrolledInterpretabilityen_US
dc.subject.pquncontrolledNatural language processingen_US
dc.titleTowards Human-AI Cooperation on Sequential Decision Making Problemsen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Feng_umd_0117E_22021.pdf
Size:
2.71 MB
Format:
Adobe Portable Document Format
Download
(RESTRICTED ACCESS)

Collections

UMD Theses and Dissertations
Computer Science Theses and Dissertations