Dynamic memorization characteristics in neural networks with different neuronal dynamics |
| |
Authors: | Katada Naofumi Nishimura Haruhiko |
| |
Affiliation: | Graduate School of Applied Informatics, University of Hyogo, Chuo-ku, Kobe, Hyogo 650-0044, Japan. nkatada@hyogo-c.ed.jp |
| |
Abstract: | We introduce a stimulus-response scheme that supports plastic variation of synapse weights in neural networks, and analyze how memory formation evolves under external stimulation. In so doing, chaotic networks and stochastic networks that have very different dynamics are compared. Experimental results suggest that chaotic activity remarkably outperforms stochastic activity in stimulus-response memorization. This seems to be indicative of effectiveness of the chaos in dynamic learning by stimulus-response scheme oriented to natural learning. |
| |
Keywords: | |
本文献已被 PubMed 等数据库收录! |
|