Competition improves robustness against loss of information
| Autor: | Kolankeh, Arash Kermani, Teichmann, Michael, Hamker, Fred H. |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
info:eu-repo/classification/ddc/000
ddc:000 info:eu-repo/classification/ddc/500 ddc:500 info:eu-repo/classification/ddc/600 ddc:600 Wettbewerb Laterale Inhibition Unabhängige Komponentenanalyse Wettbewerb Laterale Inhibition Hebbsches Lernen Unabhängige Komponentenanalyse Nicht-negative Matrixzerlegung Verdeckung Informationsverlust Technische Universität Chemnitz Publikationsfonds competition lateral inhibition Hebbian learning independent component analysis non-negative matrix factorization predictive coding/biased competition occlusion information loss Technische Universität Chemnitz Publication funds |
| Zdroj: | Front. Comput. Neurosci., 25 March 2015 | doi: 10.3389/fncom.2015.00035 |
| Druh dokumentu: | Článek |
| ISSN: | 1662-5188 |
| DOI: | 10.3389/fncom.2015.00035 |
| Popis: | 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. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|