Presentation | 2014-01-21 Self-Organization of Orientation Preference Map Based on Bar-shaped Patterns N. TAKAHASHI, J. KUROIWA, T. ODAKA, I. SUWA, SHIRAI.H. S, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we investigate effects of the learning constant in self-organizing an orientation preference map based on bar-shaped patterns. We have shown the orientation preference map is self-organized with the cluster learning, which introduce an activation of neighboring neurons into Hebbian learning, in a two-layered neural network model consisting of formal neurons. We evaluated a steady output in the output layer for a certain input by assuming that a steady state of the learning is attained. Under the the assumption of the steady state of the learning, the cluster learning plays one of important roles in forming the orientation preference map similar to biological results. However if we perform the learning slowly without the assumption, we could self-organize the orientation preference. Therefore, the purpose of this paper is to investigate the self-organization of the orientation preference by changing the leaning constant variously. In addition, we employ two learning methods, Hebbian learning and cluster learning. For small learning constants, both methods can form the orientation preference similar to biological results. However, for larger learning constants, the orientation preference given by Hebbian learning lack the smooth orientation changes more often than the cluster learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Self-organisation / Orientation preference map / Neuron model / Cluster learning rule |
Paper # | NLP2013-130 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2014/1/14(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Nonlinear Problems (NLP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Self-Organization of Orientation Preference Map Based on Bar-shaped Patterns |
Sub Title (in English) | |
Keyword(1) | Self-organisation |
Keyword(2) | Orientation preference map |
Keyword(3) | Neuron model |
Keyword(4) | Cluster learning rule |
1st Author's Name | N. TAKAHASHI |
1st Author's Affiliation | Graduate School of Engineering, University of Fukui() |
2nd Author's Name | J. KUROIWA |
2nd Author's Affiliation | Graduate School of Engineering, University of Fukui |
3rd Author's Name | T. ODAKA |
3rd Author's Affiliation | Graduate School of Engineering, University of Fukui |
4th Author's Name | I. SUWA |
4th Author's Affiliation | Graduate School of Engineering, University of Fukui |
5th Author's Name | SHIRAI.H. S |
5th Author's Affiliation | Faculty of Engineering, University of Fukui |
Date | 2014-01-21 |
Paper # | NLP2013-130 |
Volume (vol) | vol.113 |
Number (no) | 383 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |