A morphological auto-associative memory based on dendritic computing

Author

Ritter, Gerhard X. ; Iancu, Laurentiu

Author_Institution

Dept. of CISE, Florida Univ., Gainesville, FL, USA

Volume

2

fYear

2004

fDate

25-29 July 2004

Firstpage

915

Abstract

This paper presents a model of an artificial neural network whose neurons are endowed with dendritic structures and have a computational framework based on lattice algebra. Such neurons bear closer resemblance to their biological counterpart than other current artificial models. Employing a two-layer dendritic network model, we construct an auto-associative memory which is robust in the presence of random noise. Furthermore, unlike the kernel method, this memory does not require that the original patterns satisfy any conditions of morphological independence.

Keywords

algebra; content-addressable storage; dendritic structure; neural nets; random noise; artificial neural network; dendritic computing; dendritic structures; kernel method; lattice algebra; morphological autoassociative memory; random noise; two layer dendritic network model; Artificial neural networks; Associative memory; Biological neural networks; Biological system modeling; Brain modeling; Kernel; Lattices; Neurons; Noise robustness; Prototypes;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1380052

Filename

1380052