Architectures for nanoelectronic implementation of artificial neural networks: new results

Authors:
Özgür Türel;Jung Hoon Lee;Xiaolong Ma;Konstantin K. Likharev
Affiliations:
Stony Brook University, Stony Brook, NY 11794-3800, USA;Stony Brook University, Stony Brook, NY 11794-3800, USA;Stony Brook University, Stony Brook, NY 11794-3800, USA;Stony Brook University, Stony Brook, NY 11794-3800, USA
Venue:
Neurocomputing
Year:
2005

Citing 1
Cited 2

Introduction to the Theory of Neural Computation

Introduction to the Theory of Neural Computation

Artificial neural networks in hardware: A survey of two decades of progress

Neurocomputing
NanoCMOS-molecular realization of rijndael

CHES'06 Proceedings of the 8th international conference on Cryptographic Hardware and Embedded Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

Hybrid semiconductor/molecular (''CMOL'') circuits may be used for hardware implementation of artificial neural network. Our studies show that such networks (''CrossNets'') may eventually exceed the mammal brain in areal density, at much higher speed and acceptable power consumption. In this report, we demonstrate that CrossNets based on simple (two-terminal) molecular devices can work well in at least two modes: as Hopfield networks with high defect tolerance, and multilayer perceptrons.