Cargando…
Competition improves robustness against loss of information
A substantial number of works have aimed at modeling the receptive field properties of the primary visual cortex (V1). Their evaluation criterion is usually the similarity of the model response properties to the recorded responses from biological organisms. However, as several algorithms were able t...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4373393/ https://www.ncbi.nlm.nih.gov/pubmed/25859211 http://dx.doi.org/10.3389/fncom.2015.00035 |
_version_ | 1782363334001033216 |
---|---|
author | Kermani Kolankeh, Arash Teichmann, Michael Hamker, Fred H. |
author_facet | Kermani Kolankeh, Arash Teichmann, Michael Hamker, Fred H. |
author_sort | Kermani Kolankeh, Arash |
collection | PubMed |
description | A substantial number of works have aimed at modeling the receptive field properties of the primary visual cortex (V1). Their evaluation criterion is usually the similarity of the model response properties to the recorded responses from biological organisms. However, as several algorithms were able to demonstrate some degree of similarity to biological data based on the existing criteria, we focus on the robustness against loss of information in the form of occlusions as an additional constraint for better understanding the algorithmic level of early vision in the brain. We try to investigate the influence of competition mechanisms on the robustness. Therefore, we compared four methods employing different competition mechanisms, namely, independent component analysis, non-negative matrix factorization with sparseness constraint, predictive coding/biased competition, and a Hebbian neural network with lateral inhibitory connections. Each of those methods is known to be capable of developing receptive fields comparable to those of V1 simple-cells. Since measuring the robustness of methods having simple-cell like receptive fields against occlusion is difficult, we measure the robustness using the classification accuracy on the MNIST hand written digit dataset. For this we trained all methods on the training set of the MNIST hand written digits dataset and tested them on a MNIST test set with different levels of occlusions. We observe that methods which employ competitive mechanisms have higher robustness against loss of information. Also the kind of the competition mechanisms plays an important role in robustness. Global feedback inhibition as employed in predictive coding/biased competition has an advantage compared to local lateral inhibition learned by an anti-Hebb rule. |
format | Online Article Text |
id | pubmed-4373393 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2015 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-43733932015-04-09 Competition improves robustness against loss of information Kermani Kolankeh, Arash Teichmann, Michael Hamker, Fred H. Front Comput Neurosci Neuroscience A substantial number of works have aimed at modeling the receptive field properties of the primary visual cortex (V1). Their evaluation criterion is usually the similarity of the model response properties to the recorded responses from biological organisms. However, as several algorithms were able to demonstrate some degree of similarity to biological data based on the existing criteria, we focus on the robustness against loss of information in the form of occlusions as an additional constraint for better understanding the algorithmic level of early vision in the brain. We try to investigate the influence of competition mechanisms on the robustness. Therefore, we compared four methods employing different competition mechanisms, namely, independent component analysis, non-negative matrix factorization with sparseness constraint, predictive coding/biased competition, and a Hebbian neural network with lateral inhibitory connections. Each of those methods is known to be capable of developing receptive fields comparable to those of V1 simple-cells. Since measuring the robustness of methods having simple-cell like receptive fields against occlusion is difficult, we measure the robustness using the classification accuracy on the MNIST hand written digit dataset. For this we trained all methods on the training set of the MNIST hand written digits dataset and tested them on a MNIST test set with different levels of occlusions. We observe that methods which employ competitive mechanisms have higher robustness against loss of information. Also the kind of the competition mechanisms plays an important role in robustness. Global feedback inhibition as employed in predictive coding/biased competition has an advantage compared to local lateral inhibition learned by an anti-Hebb rule. Frontiers Media S.A. 2015-03-25 /pmc/articles/PMC4373393/ /pubmed/25859211 http://dx.doi.org/10.3389/fncom.2015.00035 Text en Copyright © 2015 Kermani Kolankeh, Teichmann and Hamker. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Kermani Kolankeh, Arash Teichmann, Michael Hamker, Fred H. Competition improves robustness against loss of information |
title | Competition improves robustness against loss of information |
title_full | Competition improves robustness against loss of information |
title_fullStr | Competition improves robustness against loss of information |
title_full_unstemmed | Competition improves robustness against loss of information |
title_short | Competition improves robustness against loss of information |
title_sort | competition improves robustness against loss of information |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4373393/ https://www.ncbi.nlm.nih.gov/pubmed/25859211 http://dx.doi.org/10.3389/fncom.2015.00035 |
work_keys_str_mv | AT kermanikolankeharash competitionimprovesrobustnessagainstlossofinformation AT teichmannmichael competitionimprovesrobustnessagainstlossofinformation AT hamkerfredh competitionimprovesrobustnessagainstlossofinformation |