Some results on the modelling, analysis, and design of neural networks

Author

Michel, A.N. ; Farrell, J.A. ; Gray, D.L. ; Porod, Wolfgang

Author_Institution

Dept. of Electr. & Comput. Eng., Notre Dame Univ., IN, USA

fYear

1989

Firstpage

482

Abstract

The authors cite selected papers on neural networks to give a perspective on the present subject matter. They then discuss their own work dealing with the local stability analysis of equilibrium points in the continuous Hopfield model. The authors summarize (global) analysis and synthesis results for a class of neural networks which includes as a special case the continuous Hopfield model. They summarize analysis and synthesis results for a class of neural networks with variable structure, which correspond to the discrete Hopfield model. Also summarized are the analysis and design results for a class of neural networks which are modeled by linear analog circuits that are allowed to operate in saturated modes. Specific applications of neural networks to sorting problems are also presented

Keywords

analogue computer circuits; neural nets; sorting; stability; continuous Hopfield model; equilibrium points; global analysis; linear analog circuits; local stability analysis; neural networks; saturated modes; sorting problems; variable structure; Biology computing; Hopfield neural networks; Integrated circuit interconnections; Intelligent networks; Large-scale systems; Network synthesis; Neural networks; Nonlinear dynamical systems; Stability; Symmetric matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1989., IEEE International Symposium on

Conference_Location

Portland, OR

Type

conf

DOI

10.1109/ISCAS.1989.100395

Filename

100395