Back to search

Georgia Institute of Technology

Explaining model decisions and fixing them via human feedback

Abstract

dc:description.abstract

Deep networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. While these models enable superior performance, their increasing complexity and lack of decomposability into individually intuitive components makes them hard to interpret. Consequently, when today’s intelligent systems fail, they fail spectacularly disgracefully, giving no warning or explanation. Towards the goal of making deep networks interpretable, trustworthy and unbiased, in this dissertation, we will present my work on building algorithms that provide explanations for decisions emanating from deep networks in order to — 1. understand/interpret why the model did what it did, 2. enable knowledge transfer between humans and AI, 3. correct unwanted biases learned by AI models, and 4. encourage human-like reasoning in AI.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2020

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ramasamy Selvaraju, Ramprasaath
Advisor dc:contributor.advisor
  • Parikh, Devi
Committee members dc:contributor.committeemember
  • Batra, Dhruv
  • Hoffman, Judy
  • Lee, Stefan
  • Kim, Been

Subjects

dc:subject × 6

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/62867

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ramasamy Selvaraju, Ramprasaath. Explaining model decisions and fixing them via human feedback. Doctoral thesis, Georgia Institute of Technology, 2020. http://hdl.handle.net/1853/62867