An organized view of reservoir computing: a perspective on theory and technology development

Abstract

Reservoir computing is an unconventional computing paradigm that uses system complexity and dynamics as computational medium. Currently it is the leading computational paradigm in the fields of unconventional in materia computing. This review briefly outlines the theory behind the term ‘reservoir computing’, presents the basis for evaluation of reservoirs and presents a cultural reference of reservoir computing in haiku. The summary highlights recent advances in physical reservoir computing and points out the importance of the drive, usually neglected in physical implementations of reservoir computing. However, drive signals may further simplify the training of reservoirs’ readout layer training, thus contributing to improved performance of reservoir computer performance.

Large sampling intervals for learning and predicting chaotic systems with reservoir computing

“…Derived from the traditional RNN but with lower training cost and simpler hardware implementation, RC is an efficient artificial neural network more suitable for processing time series signals with good nonlinear mapping ability, self-learning adaptation ability, and parallel information processing capacity [27][28][29][30][31][32]. Compared to other neural network algorithms, the training process of RC is simple and fast [11,[33][34][35][36][37].…”