자료유형  

 학위논문

Control Number  

0016932236

International Standard Book Number  

9798379718015

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Ramaswamy, Vikram V.

Publication, Distribution, etc. (Imprint  

[S.l.] : Princeton University., 2023

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Physical Description  

1 online resource(198 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

General Note  

Advisor: Russakovsky, Olga.

Dissertation Note  

Thesis (Ph.D.)--Princeton University, 2023.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Over the past decade the rapid increase in the ability of computer vision models has led to their applications in a variety of real-world applications from self-driving cars to medical diagnoses. However, there is increasing concern about the fairness and transparency of these models. In this thesis, we tackle these issue of bias within these models along two different axes.First, we consider the datasets that these models are trained on. We use two different methods to create a more balanced training dataset. First, we create a synthetic balanced dataset by sampling strategically from the latent space of a generative network. Next, we explore the potential of creating a dataset through a method other than scraping the internet: we solicit images from workers around the world, creating a dataset that is balanced across different geographical regions. Both techniques are shown to help create models with less bias.Second, we consider methods to improve interpretability of these models, which can then reveal potential biases within the model. We investigate a class of interpretability methods called concept-based methods that output explanations for models in terms of human understandable semantic concepts. We demonstrate the need for more careful development of the datasets used to learn the explanation as well as the concepts used within these explanations. We construct a new method that allows for users to select a trade-off between the understandability and faithfulness of the explanation. Finally, we discuss how methods that completely explain a model can be developed, and provide heuristics for the same.

Subject Added Entry-Topical Term  

Computer science.

Index Term-Uncontrolled  

Concept-based explanations

Index Term-Uncontrolled  

ML systems

Index Term-Uncontrolled  

Computer vision

Index Term-Uncontrolled  

Medical diagnoses

Index Term-Uncontrolled  

Real-world applications

Added Entry-Corporate Name  

Princeton University Computer Science

Host Item Entry  

Dissertations Abstracts International. 84-12B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:639128