Learning In Lattice Neural Networks that Employ Dendritic Computing

Author

Ritter, Gerhard X. ; Schmalz, Mark S.

Author_Institution

Univ. of Florida, Gainesville

fYear

0

fDate

0-0 0

Firstpage

7

Lastpage

13

Abstract

Recent discoveries in neuroscience imply that the basic computational elements are the dendrites that make up more than 50% of a cortical neuron´s membrane. Neuroscientists now believe that the basic computation units are dendrites, capable of computing simple logic functions. This paper discusses two types of neural networks that take advantage of these new discoveries. The focus of this paper is on some learning algorithms in the two neural networks. Learning is in terms of lattice computations that take place in the dendritic structure as well as in the cell body of the neurons used in this model.

Keywords

feedforward neural nets; learning (artificial intelligence); pattern recognition; cortical neuron membrane; dendritic computing; lattice associative memory; lattice neural network learning; neuroscience; pattern recognition; single layer feed-foward neural network; Artificial neural networks; Biological neural networks; Biomembranes; Cerebral cortex; Computer networks; Information science; Intelligent networks; Lattices; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 2006 IEEE International Conference on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-9488-7

Type

conf

DOI

10.1109/FUZZY.2006.1681687

Filename

1681687