Investigation of Elementary Cellular Automata for Reservoir Computing
Abstract
Reservoir computing is an approach to machine learning. Typical reservoir computingapproaches use large, untrained artificial neural networks to transform an input signal. Toproduce the desired output, a readout layer is trained using linear regression on the neuralnetwork.
Recently, several attempts have been made using other kinds of dynamic systemsinstead of artificial neural networks. Cellular automata are an example of a dynamic sys-tem that has been proposed as a replacement.-
This thesis attempts to discover whether cellular automata are a viable candidate foruse in reservoir computing. Four different tasks solved by other reservoir computing sys-tems are attempted with elementary cellular automata, a limited subset of all possiblecellular automata. The effect of changing different properties of the cellular automataare investigated, and the results are compared with the results when performing the sameexperiments with typical reservoir computing systems.
Reservoir computing seems like a potentially very interesting utilization of cellularautomata. However, it is evident that more research into this field is necessary to reachperformance comparable to existing reservoir computing systems.