Title :
Dynamics of associative memory with a self-consistent noise
Author_Institution :
Dept. of Phys., Bucharest Univ.
fDate :
31 Aug-2 Sep 1995
Abstract :
The Glauber dynamics of magnetic systems has been extended to the case of neural networks with a general odd response function. The author derives a set of recursion relations for the overlap parameter, noise average and noise variance taken as macrovariables of the process describing the dynamics of associative memory. The retrieval process is studied then for a hyperbolic tangent transfer function by the self-consistent signal to noise ratio method. It takes into account the fatigue effect of the real neuron. The phase diagrams of the retrieval process reveals an enhanced storage capacity for a certain set of parameter values
Keywords :
content-addressable storage; dynamics; neural nets; probability; transfer functions; Glauber dynamics; associative memory; enhanced storage capacity; hyperbolic tangent transfer function; magnetic systems; noise average; noise variance; odd response function; recursion relations; retrieval process; self-consistent signal to noise ratio method; Associative memory; Equations; Fatigue; Magnetic noise; Neural networks; Neurons; Signal processing; Signal to noise ratio; Stochastic processes; Transfer functions;
Conference_Titel :
Neural Networks for Signal Processing [1995] V. Proceedings of the 1995 IEEE Workshop
Conference_Location :
Cambridge, MA
Print_ISBN :
0-7803-2739-X
DOI :
10.1109/NNSP.1995.514890
