Title :
Quick learning for multidirectional associative memories
Author :
Hattori, Motonobu ; Hagiwara, Masafumi
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
In this paper, a quick learning algorithm for multidirectional associative memories (MAMs) is proposed. With this quick learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers, and the relation between the noise reduction effect and the number of layers are introduced
Keywords :
Hebbian learning; associative processing; content-addressable storage; neural nets; Hebbian learning; multidirectional associative memories; neural networks; noise reduction effect; quick learning algorithm; storage capacity; Associative memory; Hebbian theory; Humans; Image coding; Magnesium compounds; Noise reduction; Parallel processing; Psychology; Reverberation; Training data;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488969
