Presentation | 1996/3/18 Neuronal Model Dependences for the Randomly and Symmetrically Connected Networks Akira Date, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A large number of equilibrium states or fixed points is in a randomly and symmetrically connected neural network. Recently it has been shown that the maximum number which can be realized in the network depend on the binary model of single neurons (Date et al 1995). Here we treat such network properties of the model dependence including the maximum number of equilibrium states and the activity level (i.e. the rate of excited neurons) of these states. It is analytically shown that the (-1, 1) network, the network consisting of the elements each of which takes -1 or 1 as a output, is the best in a sense of maximizing the number of equilibrium states. Furthermore, the invariant activity in each model is also analytically derived, where the activity does not depend on the statistical parameters designated by the probability distribution of the connection weights and the threshold. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | random symmetric networks / SK-model / equilibrium states / statistical neurodynamics |
Paper # | NC-95-123 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1996/3/18(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 | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Neuronal Model Dependences for the Randomly and Symmetrically Connected Networks |
Sub Title (in English) | |
Keyword(1) | random symmetric networks |
Keyword(2) | SK-model |
Keyword(3) | equilibrium states |
Keyword(4) | statistical neurodynamics |
1st Author's Name | Akira Date |
1st Author's Affiliation | Department of Computer Science, Graduate School of Technology Tokyo University of Agriculture & Technology() |
Date | 1996/3/18 |
Paper # | NC-95-123 |
Volume (vol) | vol.95 |
Number (no) | 598 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |