Neuromorphic Electronic Systems for Reservoir Computing

Abstract

This chapter provides a comprehensive survey of the researches and motivations for hardware implementation of reservoir computing (RC) on neuromorphic electronic systems. Due to its computational efficiency and the fact that training amounts to a simple linear regression, both spiking and non-spiking implementations of reservoir computing on neuromorphic hardware have been developed. Here, a review of these experimental studies is provided to illustrate the progress in this area and to address the technical challenges which arise from this specific hardware implementation. Moreover, to deal with challenges of computation on such unconventional substrates, several lines of potential solutions are presented based on advances in other computational approaches in machine learning.

Design of ANN Based Non-Linear Network Using Interconnection of Parallel Processor

“…Much of the research is focused on ANN. It is gaining vast importance among the young researchers for the reason that they are a lot of improvisations in ANN, and similar algorithms were suggested by Hinton, Williams, and Rumelhart [2] also, significant improvement was suggested in the ANN theoretical concepts by Fukushima [3], Grossberg [4] and Zubair et al [5], significantly value-added ANN methods were proposed for solving simulation problems with modified techniques [6][7][8][9]. Outstanding assessments of the past improvements in neural computation can be seen in Windrow et al [10], and the book [11].…”