The hysteretic Hopfield neural network

Author

Bharitkar, Sunil ; Mendel, Jerry M.

Author_Institution

Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA, USA

Volume

11

Issue

4

fYear

2000

fDate

7/1/2000 12:00:00 AM

Firstpage

879

Lastpage

888

Abstract

A new neuron activation function based on a property found in physical systems-hysteresis-is proposed. We incorporate this neuron activation in a fully connected dynamical system to form the hysteretic Hopfield neural network (HHNN). We then present an analog implementation of this architecture and its associated dynamical equation and energy function. We proceed to prove Lyapunov stability for this new model, and then solve a combinatorial optimization problem (i.e., the N-queen problem) using this network. We demonstrate the advantages of hysteresis by showing increased frequency of convergence to a solution, when the parameters associated with the activation function are varied

Keywords

Hopfield neural nets; Lyapunov methods; convergence; hysteresis; stability; transfer functions; HHNN; Lyapunov stability; N-queen problem; activation function; combinatorial optimization problem; dynamical equation; energy function; fully connected dynamical system; hysteretic Hopfield neural network; neuron activation function; Animal structures; Biological neural networks; Circuits; Equations; Frequency; Hopfield neural networks; Hysteresis; Immune system; Lyapunov method; Neurons;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.857769

Filename

857769