Presentation | 2006-05-26 Network structure after time sequence learning Daichi KIMURA, Yoshinori HAYAKAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We analyze how the structure of neural networks changes by the nature of task. We assume the synapses whose weight is large are dominant in neural network, and we remove the synapses whose weight is small from the network after learning. As a result of analysis, we found that the number of loops of network depends on the tasks having different temporal redundancy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Complex Network / Self Organization |
Paper # | NC2006-7 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2006/5/19(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 | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Network structure after time sequence learning |
Sub Title (in English) | |
Keyword(1) | Complex Network |
Keyword(2) | Self Organization |
1st Author's Name | Daichi KIMURA |
1st Author's Affiliation | Faculty of Science, Tohoku University() |
2nd Author's Name | Yoshinori HAYAKAWA |
2nd Author's Affiliation | Faculty of Science, Tohoku University |
Date | 2006-05-26 |
Paper # | NC2006-7 |
Volume (vol) | vol.106 |
Number (no) | 79 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |