Towards Understanding Human-aligned Neural Representation in the Presence of Confounding Variables

Deep Neural Networks (DNNs) find one out of many possible solutions to a given task such as classification. This solution is more likely to pick up on spurious features and low-level statistical patterns in the train data rather than semantic features and highlevel abstractions, resulting in poor Out-of-Distribution (OOD) performance. In this project we aim to broaden the current knowledge surrounding spurious correlations as they relate to DNNs. We do this by measuring their effect on generalization under various settings, determining the existence of subnetworks in a DNN that capture the core features and examine potential mitigation strategies. Finally, we discuss alternative approaches that are reserved for future work.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2021

Author dc:creator

• Simonovikj, Sanja

Advisor dc:contributor.advisor

• Agrawal, Pulkit

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright MIT

Licence dc:rights.uri

• http://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/139079

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/139079