Title :
Engram decay in artificial neural networks
Author :
Copland, Howard ; Hendtlass, Tim
Author_Institution :
Centre for Intelligent Syst., Swinburne Univ. of Technol., Hawthorn, Vic., Australia
Abstract :
In this paper the process of forgetting, termed “engram decay”, in artificial neural networks is examined for three classes of networks: the self organizing map, fuzzy logic adaptive resonance theory and, maximally connected backpropagation networks. All networks were trained to categorize three varieties of iris. How iris categories are forgotten is shown to be strongly related to the distribution of iris categories in feature space
Keywords :
ART neural nets; backpropagation; feedforward neural nets; fuzzy neural nets; self-organising feature maps; backpropagation networks; engram decay; feature space; forgetting process; fuzzy logic adaptive resonance theory; iris categories; learning; self organizing map; Artificial intelligence; Artificial neural networks; Australia; Backpropagation; Biological neural networks; Biological system modeling; Fuzzy logic; Intelligent networks; Intelligent systems; Iris; Organizing; Resonance; Waveguide discontinuities;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488260
