A spatial deep network architecture for brain decoding

We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate structured smoothness in a deep learning model. FGL achieves this goal by connecting nodes across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on behaviour are smoothed. Experimental results on simulated and real data is provided. Our proposed model architecture performs better than conventional neural network architectures.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2019

Author dc:creator

• Habeeb, Haroun

Contributors dc:contributor

• Koyejo, Oluwasanmi

• Machine Learning
• Brain Decoding
• Deep Learning

Statement dc:rights

• Copyright 2019 Haroun Habeeb

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/104898

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/104898