Functional differentiations in evolutionary reservoir computing networks
This work addresses a domain-specific problem in neural network design for researchers in reservoir computing, but it appears incremental as it extends existing methods with evolutionary dynamics.
The authors tackled the problem of enabling functional differentiation of neurons in reservoir computing by proposing an evolutionary reservoir computer that controls internal dynamics to produce specificity based on input information, resulting in the development of specific neuronal units through sequential expanding and contracting dynamics.
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.