Back to search

Georgia Institute of Technology

Contrastive Reasoning in Neural Networks

Abstract

dc:description.abstract

The objective of the dissertation is to rethink the inductive nature of reasoning in neural networks by providing contextual explanations to a network’s decision and addressing the network's robustness capabilities. Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify dependencies within this manifold is termed as inductive feed-forward inference. This is a classical cause-to-effect inference model that is widely used because of its simple mathematical functionality and ease of operation. Nevertheless, feed-forward models do not generalize well to untrained situations. To alleviate this generalization challenge, we use an effect-to-cause inference model that falls under the abductive reasoning framework. Here, the features represent the change from existing weight dependencies given a certain effect. In this dissertation, we term this change as contrast and the ensuing inference mechanism as contrastive inference. While existing works on contrastive learning consider the contrast between data, we consider the contrast between decisions. As such, we create meta-representations, which are functions of data and models, to reason about given inputs. The dissertation tackles contrastive reasoning and inference in three phases: 1) We formalize the structure of contrastive reasons as answers to questions of the form `Why P, rather than Q?' and provide a simple mechanism to extract contrastive reasons from any pre-trained neural network, 2) We analyze our contrastive reasons by creating a taxonomy of evaluation, and 3) Use contrastive reasons to make robust and generalizable decisions. We provide representational and explanatory insights using our contrastive reasoning scheme for diverse visual applications including: 1) Visual cognition-based human attention, 2) Probabilistic modeling of causal and context features, 3) Active learning paradigm of machine learning, and 4) Meta-representations within neural networks.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Electrical and Computer Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2021

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Prabhushankar, Mohit
Advisor dc:contributor.advisor
  • AlRegib, Ghassan
Committee members dc:contributor.committeemember
  • Davenport, Mark
  • Riedl, Mark
  • Dyer, Eva
  • Heck, Larry

Subjects

dc:subject × 7

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/70076

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

Prabhushankar, Mohit. Contrastive Reasoning in Neural Networks. Doctoral thesis, Georgia Institute of Technology, 2021. http://hdl.handle.net/1853/70076