Generating novel memories by integration of chaotic neural network modules |
| |
Authors: | Akira Sano |
| |
Affiliation: | (1) Graduate School of Informatics, Kyoto University, Yoshida-Honmachi, Sakyo-ku, 606-8501 Kyoto, Japan;(2) Present address: Department of Applied Mathematics and Informatics, Ryukoku University, 1-5 Yokotani, Seta, Ohe-machi, 520-2194 Otsu, Japan |
| |
Abstract: | A principle of integrating neural network modules based on chaotic dynamics was studied on our two-moduled Nozawa model. Chaotic
neural networks represent each embedded pattern as a low-dimensional periodic orbit, and the others are shown as high-dimensional
chaotic attractors. This is equivalent to W. Freeman’s “I don’t know” and “I know” states. In particular, we noted that the combination of two-way inputs to each neural network module conflicted with embedded
Hebbian correspondence. It was found that the interaction between the modules generated a novel “I know” state in addition to the embedded representation. Chaotic neural network modules can autonomously generate novel memories
or functions by this interaction. The result suggests a functional integration in neural networks as it ought to be, e.g.,
feature binding and gestalt.
This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January
19–22, 1999 |
| |
Keywords: | Modularity Chaotic neural network Autonomous integration Hebbian learning |
本文献已被 SpringerLink 等数据库收录! |
|