Title :
On the analysis of dynamic feedback neural nets
Author :
Salam, Fathi M A ; Wang, Yiwen ; Choi, Myung-Ryul
Author_Institution :
Dept. of Electr. Eng. & Syst. Sci., Michigan State Univ., East Lansing, MI, USA
fDate :
2/1/1991 12:00:00 AM
Abstract :
A formulation for dynamic feedback neural networks of the Hopfield type is presented. A description is given of the general design framework used, in which a neural network would only have a finite number of memories. Some basic properties of the nonzero equilibria as well as the (unstable) equilibrium point at zero in the proposed framework are also discussed
Keywords :
feedback; neural nets; poles and zeros; stability; Hopfield type; design framework; dynamic feedback neural nets; equilibrium point stability; nonzero equilibria; Artificial neural networks; Associative memory; Biological neural networks; Integrated circuit interconnections; Neural networks; Neurofeedback; Optical computing; Optical feedback; Optical interconnections; Pattern recognition;
Journal_Title :
Circuits and Systems, IEEE Transactions on
