Presentation | 2003/12/1 Phaser Neural Network and Mean Field Approximation Haruhisa TAKAHASHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We present a new deterministic network model of representing correlated activation between neurons. The model is represented by a set of complex neural equations computing fire timing as a phase, and of mean field equations computing the mean firing rate. We show that the mean field equations provide a good approximation to stochastic neural model such as Boltzman machine even for large parameter values. We also show that Boltzman learning method is simply replaced by a combination of covariance Hebbian and anti-Hebbian learning on this model. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | phasor / covariance netowork / Boltsmann machine / graphical model |
Paper # | NC2003-101 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2003/12/1(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) | Phaser Neural Network and Mean Field Approximation |
Sub Title (in English) | |
Keyword(1) | phasor |
Keyword(2) | covariance netowork |
Keyword(3) | Boltsmann machine |
Keyword(4) | graphical model |
1st Author's Name | Haruhisa TAKAHASHI |
1st Author's Affiliation | Department of Infromation and Communication Engineering The University of Electro-Communications() |
Date | 2003/12/1 |
Paper # | NC2003-101 |
Volume (vol) | vol.103 |
Number (no) | 490 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |