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, the 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.
Functional differentiations in evolutionary reservoir computing networks
Note: This paper is part of the Focus Issue, Chaos: From Theory to Applications.
Yutaka Yamaguti, Ichiro Tsuda; Functional differentiations in evolutionary reservoir computing networks. Chaos 1 January 2021; 31 (1): 013137. https://doi.org/10.1063/5.0019116
Download citation file: