Back to search

Cornell University

Insights from Deep Representations for Machine Learning Systems and Human Collaborations

Abstract

dc:description.abstract

Over the past several years, we have witnessed fundamental breakthroughs in machine learning, largely driven by rapid advancements of the underlying deep neural network models and algorithms. This has consequently spurred the development of new, powerful machine learning systems, with emerging applications in specialized, high-stakes domains such as medicine. However, the increased capabilities of these novel systems come at a cost of much greater complexity, with the design of machine learning systems becoming ever more laborious, computationally expensive and opaque. This can result in catastrophic failures and significantly hinders effective collaboration with human experts, often central to successful deployment. In this thesis, we present research results that take steps to addressing these challenges. Having first overviewed some of the key deep learning models, algorithms and use cases, we begin by introducing quantitative techniques that can give insights into neural network hidden representations, which provide both fundamental understanding on central aspects of machine learning, and also inform algorithms for efficiently learning and training these complex systems. Finally, we study how these fully trained AI systems can be adapted to work effectively with human experts, resulting in better outcomes than either humans or AI alone. We conclude with a discussion on the many rich further directions and open questions for future study.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2020

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Raghu, Maithreyi
Chair dc:contributor.chair
  • Kleinberg, Jon M.
Committee members dc:contributor.committeemember
  • Kleinberg, Robert David
  • Weinberger, Kilian Quirin

Rights

dc:rights
Statement dc:rights
  • Attribution-NoDerivatives 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
13277969
Dc Identifier Other
ProQuest Submission ID: 12141
ProQuest Publication ID: 28030724

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Raghu, Maithreyi. Insights from Deep Representations for Machine Learning Systems and Human Collaborations. Doctor of Philosophy thesis, Cornell University, 2020. https://hdl.handle.net/1813/103077