Improved multidirectional associative memories for training sets including common terms

Author

Hattori, Motonobu ; Hagiwara, Masafumi ; Nakagawa, Masao

Author_Institution

Dept. of Electr. Eng., Keio Univ., Japan

Volume

2

fYear

1992

fDate

7-11 Jun 1992

Firstpage

172

Abstract

Improved multidirectional associative memories (IMAMs) are proposed and simulated. The IMAM fundamental component is a multilayer neural network. IMAMs can memorize and recall multiple associations even when training sets include common terms, such as the training sets composed of (A,a,1), (A,b,2), (C ,b,3). The structure of the proposed IMAMs is represented by mutual connections of multilayer neural networks. The proposed IMAMs require less parameters compared with other associative memories and are capable of automatic recall. Recall performance can be greatly improved by using a priority coefficient

Keywords

content-addressable storage; feedforward neural nets; learning (artificial intelligence); automatic recall; multidirectional associative memories; multilayer neural network; multiple associations; priority coefficient; recall performance; training sets; Associative memory; Automatic control; Biological neural networks; Humans; Multi-layer neural network; Neural networks; Neurofeedback; Nonhomogeneous media; Parallel processing; Psychology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.227012

Filename

227012