DocumentCode
3308227
Title
Storage Capacity of the Hopfield Network Associative Memory
Author
Wu, Yue ; Hu, Jianqing ; Wu, Wei ; Zhou, Yong ; Du, K.L.
Author_Institution
Enjoyor, Inc., Hangzhou, China
fYear
2012
fDate
12-14 Jan. 2012
Firstpage
330
Lastpage
336
Abstract
The Hop field model is a well-known dynamic associative-memory model. In this paper, we investigate various aspects of the Hop field model for associative memory. We conduct a systematic simulation investigation of several storage algorithms for Hop field networks, and conclude that the perceptron learning based storage algorithms can achieve much better storage capacity than the Hebbian learning based algorithms.
Keywords
Hebbian learning; Hopfield neural nets; content-addressable storage; perceptrons; Hebbian learning based algorithms; Hopfield network associative memory; dynamic associative-memory model; perceptron learning based storage algorithms; storage capacity; Associative memory; Hebbian theory; Hopfield neural networks; Neurons; Training; Upper bound; Vectors; Hebbian learning; Hopfield model; associative memory; perceptron learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Computation Technology and Automation (ICICTA), 2012 Fifth International Conference on
Conference_Location
Zhangjiajie, Hunan
Print_ISBN
978-1-4673-0470-2
Type
conf
DOI
10.1109/ICICTA.2012.89
Filename
6150208
Link To Document