Memristor-Based Neuron Circuit and Method for Applying Learning Algorithm in SPICE

Author(s)

Christopher Yakopcic, University of DaytonFollow
R. Hasan, University of Dayton
T.M. Taha, University of Dayton
M. McLean, Ctr Except Comp
D. Palmer, Annapolis Micro Systems

Document Type

Article

Publication Date

3-27-2014

Publication Source

Electronics Letters

Abstract

The learning of nonlinearly separable functions in cascaded memristor crossbar circuits is described and the feasibility of using them to develop low-power neuromorphic processors is demonstrated. This is the first study evaluating the training of memristor crossbars through SPICE simulations. It is important to capture the alternate current paths and wire resistance inherent in these circuits. The simulations show that neural network learning algorithms are able to train in the presence of alternate current paths and wire resistances. The fact that the approach reduces the area by three times and power by two orders of magnitude compared with the existing approaches that use virtual ground opamps to eliminate alternate current paths is demonstrated.

Inclusive pages

492-493

ISBN/ISSN

0013-5194

Document Version

Published Version

Comments

This open-access article is provided for download in compliance with the publisher’s policy on self-archiving. To view the version of record, use the DOI: https://doi.org/10.1049/el.2014.0464

Publisher

Wiley

Volume

50

Peer Reviewed

yes

Issue

7

Sponsoring Agency

National Science Foundation (NSF) ; NSF - Directorate for Computer & Information Science & Engineering (CISE)

eCommons Citation

Yakopcic, Christopher; Hasan, R.; Taha, T.M.; McLean, M.; and Palmer, D., "Memristor-Based Neuron Circuit and Method for Applying Learning Algorithm in SPICE" (2014). Electrical and Computer Engineering Faculty Publications. 450.
https://ecommons.udayton.edu/ece_fac_pub/450