Semiconductor technologies and related topics for implementation of electronic reservoir computing systems
Author:
Open Access
- 9 September 2022
- journal article
- review article
- Published by IOP Publishing in Semiconductor Science and Technology
- Vol. 37 (10) , 103001
Abstract
Reservoir computing (RC) is a unique machine learning framework based on a recurrent neural network, which is currently involved in numerous research fields. RC systems are distinguished from other machine learning systems since detailed network designs and weight adjustments are not necessary. This enables the availability of many device and material options to physically implement the system, referred to as physical RC. This review outlines the basics of RC and related issues from an implementation perspective that applies semiconductor electron device technology. A possible interpretation of RC computations is shown using a simple model, and the reservoir network is understood from the viewpoint of network theory. Physical implementation and operation issues are discussed by referring to our experimental investigation of dynamic nodes using a semiconductor tunnel diode with cubic nonlinearity.Keywords
This publication has 88 references indexed in Scilit:
- Information Processing Capacity of Dynamical SystemsScientific Reports, 2012
- Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog NeuronsNeural Computation, 2010
- Synchronization in complex networksPhysics Reports, 2008
- Carbon-based electronicsNature Nanotechnology, 2007
- Optimization and applications of echo state networks with leaky- integrator neuronsNeural Networks, 2007
- The cerebellum as a liquid state machineNeural Networks, 2007
- Characterization of complex networks: A survey of measurementsAdvances in Physics, 2007
- Constructing transcriptional regulatory networksGenes & Development, 2005
- Benchmarking Nanotechnology for High-Performance and Low-Power Logic Transistor ApplicationsIEEE Transactions on Nanotechnology, 2005
- Consistency of Nonlinear System Response to Complex Drive SignalsPhysical Review Letters, 2004