تقرير
Functional differentiations in evolutionary reservoir computing networks
| العنوان: | Functional differentiations in evolutionary reservoir computing networks |
|---|---|
| المؤلفون: | Yamaguti, Yutaka, Tsuda, Ichiro |
| المصدر: | Chaos 31, 013137 (2021) |
| سنة النشر: | 2020 |
| المجموعة: | Computer Science Nonlinear Sciences |
| مصطلحات موضوعية: | Nonlinear Sciences - Adaptation and Self-Organizing Systems, Computer Science - Neural and Evolutionary Computing |
| الوصف: | We propose an extended reservoir computer that shows the functional differentiation of neurons. The reservoir computer is developed to enable changing of the internal reservoir using evolutionary dynamics, and we call it an evolutionary reservoir computer. To develop neuronal units to show specificity, depending on the input information, the internal dynamics should be controlled to produce contracting dynamics after expanding dynamics. Expanding dynamics magnifies the difference of input information, while contracting dynamics contributes to forming clusters of input information, thereby producing multiple attractors. The simultaneous appearance of both dynamics indicates the existence of chaos. In contrast, sequential appearance of these dynamics during finite time intervals may induce functional differentiations. In this paper, we show how specific neuronal units are yielded in the evolutionary reservoir computer. Comment: Revised manuscript. 15 figures. This article has been submitted to Chaos. After it is published, it will be found at https://aip.scitation.org/journal/cha |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1063/5.0019116 |
| URL الوصول: | http://arxiv.org/abs/2006.11507 |
| رقم الأكسشن: | edsarx.2006.11507 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1063/5.0019116 |
|---|