You are here
CRACKING THE SPARSE CODE: LATERAL COMPETITION FORMS ROBUST V1-LIKE REPRESENTATIONS IN CONVOLUTIONAL NEURAL NETWORKS
- Date Issued:
- 2022
- Abstract/Description:
- Although state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust, sparse representations of sensory stimuli for downstream tasks. In this thesis, I hypothesize that CNN layers equipped with lateral competition better approximate the response characteristics and dynamics of neurons in the mammalian primary visual cortex, leading to increased robustness under noise and/or adversarial attacks relative to current robust CNN layers. To test this hypothesis, I develop a new class of CNNs called LCANets, which simulate recurrent, feature-specific lateral competition between neighboring neurons via a sparse coding model termed the Locally Competitive Algorithm (LCA). I first perform an analysis of the response properties of LCA and show that sparse representations formed by lateral competition more accurately mirror response characteristics of primary visual cortical populations and are more useful for downstream tasks like object recognition than previous sparse CNNs, which approximate competition with winner-take-all mechanisms implemented via thresholding.
Title: | CRACKING THE SPARSE CODE: LATERAL COMPETITION FORMS ROBUST V1-LIKE REPRESENTATIONS IN CONVOLUTIONAL NEURAL NETWORKS. |
![]() ![]() |
---|---|---|
Name(s): |
Teti, Michael, author Barenholtz, Elan, Thesis advisor Hahn, William , Thesis advisor Florida Atlantic University, Degree grantor Center for Complex Systems and Brain Sciences Charles E. Schmidt College of Science |
|
Type of Resource: | text | |
Genre: | Electronic Thesis Or Dissertation | |
Date Created: | 2022 | |
Date Issued: | 2022 | |
Publisher: | Florida Atlantic University | |
Place of Publication: | Boca Raton, Fla. | |
Physical Form: | application/pdf | |
Extent: | 118 p. | |
Language(s): | English | |
Abstract/Description: | Although state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust, sparse representations of sensory stimuli for downstream tasks. In this thesis, I hypothesize that CNN layers equipped with lateral competition better approximate the response characteristics and dynamics of neurons in the mammalian primary visual cortex, leading to increased robustness under noise and/or adversarial attacks relative to current robust CNN layers. To test this hypothesis, I develop a new class of CNNs called LCANets, which simulate recurrent, feature-specific lateral competition between neighboring neurons via a sparse coding model termed the Locally Competitive Algorithm (LCA). I first perform an analysis of the response properties of LCA and show that sparse representations formed by lateral competition more accurately mirror response characteristics of primary visual cortical populations and are more useful for downstream tasks like object recognition than previous sparse CNNs, which approximate competition with winner-take-all mechanisms implemented via thresholding. | |
Identifier: | FA00014050 (IID) | |
Degree granted: | Dissertation (PhD)--Florida Atlantic University, 2022. | |
Collection: | FAU Electronic Theses and Dissertations Collection | |
Note(s): | Includes bibliography. | |
Subject(s): |
Neural networks (Computer science) Machine learning Computer vision |
|
Persistent Link to This Record: | http://purl.flvc.org/fau/fd/FA00014050 | |
Use and Reproduction: | Copyright © is held by the author with permission granted to Florida Atlantic University to digitize, archive and distribute this item for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder. | |
Use and Reproduction: | http://rightsstatements.org/vocab/InC/1.0/ | |
Host Institution: | FAU | |
Is Part of Series: | Florida Atlantic University Digital Library Collections. |