Title :
Analysis and synthesis of a continuous-time hysteresis neural network
Author :
Jin´no, Kenya ; Saito, Toshimichi
Author_Institution :
Dept. of Electr. Eng., Hosei Univ., Tokyo, Japan
Abstract :
A piecewise-linear hysteresis associative memory is discussed. Conditions on parameters for guaranteed storage of all desired memories, global convergence of an energy function, and control of stable spurious output are given. The networks are then synthesized using a mixed autocorrelation/pseudoinverse matrix. In some range of their mixed rate, it is numerically confirmed that the performance is improved vastly. A remarkable hysteresis effect in the global convergence properties of each desired memory is found
Keywords :
content-addressable storage; neural nets; piecewise-linear techniques; continuous-time hysteresis neural network; energy function; global convergence; mixed autocorrelation/pseudoinverse matrix; piecewise-linear hysteresis associative memory; stable spurious output; Artificial intelligence; Biological systems; Chaos; Equations; Hysteresis; Network synthesis; Neural networks; Sufficient conditions; Vectors;
Conference_Titel :
Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0593-0
DOI :
10.1109/ISCAS.1992.229911
