Dissertation/Thesis Abstract

The Performance of Random Prototypes in Hierarchical Models of Vision
by Stewart, Kendall Lee, M.S., Portland State University, 2015, 79; 1605894
Abstract (Summary)

I investigate properties of HMAX, a computational model of hierarchical processing in the primate visual cortex. High-level cortical neurons have been shown to respond highly to particular natural shapes, such as faces. HMAX models this property with a dictionary of natural shapes, called prototypes, that respond to the presence of those shapes. The resulting set of similarity measurements is an effective descriptor for classifying images. Curiously, prior work has shown that replacing the dictionary of natural shapes with entirely random prototypes has little impact on classification performance. This work explores that phenomenon by studying the performance of random prototypes on natural scenes, and by comparing their performance to that of sparse random projections of low-level image features.

Indexing (document details)
Advisor: Mitchell, Melanie
Commitee: Liu, Feng, Walpole, Jonathan
School: Portland State University
Department: Computer Science
School Location: United States -- Oregon
Source: MAI 55/03M(E), Masters Abstracts International
Subjects: Computer science
Keywords: Computational neuroscience, Computer vision, Machine learning, Random projection
Publication Number: 1605894
ISBN: 978-1-339-34700-4
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy