| | |
| | |
Stat |
Members: 3643 Articles: 2'487'895 Articles rated: 2609
28 March 2024 |
|
| | | |
|
Article overview
| |
|
Phase Diagram and Storage Capacity of Sequence Processing Neural Networks | A. During
; A.C.C. Coolen
; D. Sherrington
; | Date: |
6 May 1998 | Subject: | Disordered Systems and Neural Networks | cond-mat.dis-nn q-bio | Abstract: | We solve the dynamics of Hopfield-type neural networks which store sequences of patterns, close to saturation. The asymmetry of the interaction matrix in such models leads to violation of detailed balance, ruling out an equilibrium statistical mechanical analysis. Using generating functional methods we derive exact closed equations for dynamical order parameters, viz. the sequence overlap and correlation- and response functions, in the thermodynamic limit. We calculate the time translation invariant solutions of these equations, describing stationary limit-cycles, which leads to a phase diagram. The effective retarded self-interaction usually appearing in symmetric models is here found to vanish, which causes a significantly enlarged storage capacity of $alpha_csim 0.269$, compared to $alpha_csim 0.139$ for Hopfield networks storing static patterns. Our results are tested against extensive computer simulations and excellent agreement is found. | Source: | arXiv, cond-mat/9805073 | Services: | Forum | Review | PDF | Favorites |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser claudebot
|
| |
|
|
|
| News, job offers and information for researchers and scientists:
| |