Title :
An unsupervised neural network with a memory replacement effect
Author :
Lee, C.K. ; Chung, C.H.
Author_Institution :
Dept. of Electron. Eng., Hong Kong Polytech., Hung Hom, Hong Kong
fDate :
27 Jun-2 Jul 1994
Abstract :
Studies the memory replacement effect of a unsupervised learning algorithm for a neural network. The unsupervised learning algorithm on which we base this effect is called `learning by experience´ (LBE). We modify the network to incorporate a replacement algorithm to increase the learning capability of the network when it faces a memory catastrophe. Simulations to illustrate the feasibility of this effect are included
Keywords :
content-addressable storage; neural nets; unsupervised learning; learning by experience; learning capability; memory catastrophe; memory replacement effect; neural network; simulations; unsupervised learning algorithm; Electrical capacitance tomography; Feedforward neural networks; Feeds; Mean square error methods; Mesons; Neural networks; Neurons; Unsupervised learning;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374257
