A Multidirectional Associative Memory Based on Self-organizing Incremental Neural Network

Hui Yu,Furao Shen,Osamu Hasegawa

doi:10.1007/978-3-642-17534-3_42

A Multidirectional Associative Memory Based on Self-organizing Incremental Neural Network

Hui Yu, Furao Shen + Show 1 more

https://doi.org/10.1007/978-3-642-17534-3_42

Copy DOI

Publication Date: Jan 1, 2010

Citations: 12

Affiliation: Nanjing University, Jiangyin Traffic Planning Survey & Design Institute (China), Tokyo Institute of Technology

#Self-organizing Incremental Neural Network #Multidirectional Associative Memory + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

A multidirectional associative memory (AM) is proposed. It is constructed with three layer networks: an input layer, a memory layer, and an associate layer. The proposed method is able to realize many-to-many associations with no predefined conditions, and the association can be incrementally added to the network without destruction of old associations. Experiments show that the proposed AM works well for real tasks.KeywordsIncremental learningSelf-organizing incremental neural networkMany-to-many association

Full Text