Title :
Analysis and synthesis of a class of discrete-time neural networks described on hypercubes
Author :
Michel, A.N. ; Si, J. ; Yen, G.
Author_Institution :
Dept. of Electr. & Comput. Eng., Notre Dame Univ., IN, USA
Abstract :
The qualitative properties of neural networks described by a system of first-order linear ordinary difference equations which are defined on a closed hypercube of the state space with solutions extended to the boundary of the hypercube are investigated. The class of systems considered can easily be implemented in digital hardware. When implemented by a serial processor (e.g., in digital simulations), the presented class of neural networks offers considerable advantages over digital simulations of the differential equations used to represent the continuous-time neural networks considered in previously published work. The applicability of the present results is demonstrated by means of several specific examples. These include pattern recognition applications
Keywords :
computerised pattern recognition; hybrid simulation; hypercube networks; neural nets; state-space methods; virtual machines; discrete-time neural networks; hypercubes; implemented in digital hardware; pattern recognition; qualitative properties; serial processor; state space; synthesis; system of first-order linear ordinary difference equations; Difference equations; Differential equations; Digital simulation; Hardware; Hypercubes; Linear systems; Network synthesis; Neural networks; State-space methods; Vectors;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112175
