A new approach to artificial neural networks

Author

Filho, Benedito Dias Baptista ; Cabral, Eduardo Lobo Lustosa ; Soares, Adalberto José

Author_Institution

Inst. de Pesquisas Energeticas e Nucl., Energetic & Nucl. Res. Inst. of the Brazilian Nucl. Energy Nat. Comm., UK

Volume

9

Issue

6

fYear

1998

fDate

11/1/1998 12:00:00 AM

Firstpage

1167

Lastpage

1179

Abstract

A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model with multiple synapses. The synapses´ connective strengths are modified through selective and cumulative processes conducted by axo-axonic connections from a feedforward circuit. This new concept was applied to the position control of a planar two-link manipulator exhibiting excellent results on learning capability and generalization when compared with a conventional feedforward network. In the present paper, the example shows only a network developed from a neuronal reflexive circuit with some useful artifices, nevertheless without the intention of covering all possibilities devised

Keywords

feedforward neural nets; generalisation (artificial intelligence); learning (artificial intelligence); manipulator dynamics; neurocontrollers; position control; feedforward neural networks; generalization; learning; multiple synapses; neurocontrol; planar two-link manipulator; position control; Artificial neural networks; Backpropagation algorithms; Circuits; Computer architecture; Control systems; Helium; Manipulator dynamics; Neurons; Position control; Transfer functions;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.728360

Filename

728360