Functional differentiations in evolutionary reservoir computing networks

TL;DR

This paper introduces an evolutionary reservoir computing network that demonstrates functional differentiation of neurons through controlled internal dynamics, combining expanding and contracting behaviors to produce specialized neuronal units.

Contribution

It presents an extended reservoir computer with evolutionary dynamics that enables the emergence of functionally differentiated neurons based on input information processing.

Findings

Neurons develop specific functions depending on input information.

The model shows the coexistence of expanding and contracting dynamics.

Functional differentiation arises through sequential dynamics during evolution.

Abstract

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.