Continuous time delay neural networks for detection of temporal patterns in signals

Author

Derakhshani, Reza ; Schuckers, Stephanie A C

Author_Institution

Dept. of Comput. Sci. & Electr. Eng., West Virginia Univ., Morgantown, WV, USA

Volume

4

fYear

2004

fDate

25-29 July 2004

Firstpage

2723

Abstract

A method for temporal pattern recognition for continuous time signals is addressed. It is shown how a simple form of back-propagation can be used in conjunction with a temporal error signal to adapt both the weights and path delays of a continuous time delay feed forward multi-layer neural network with hard-limited output. An instance of such a network is simulated and some of the results are discussed. During the initial tests the network showed robust capabilities for detection of temporal patterns, including fast recognition of onsets of new waveforms in presence of moderately heavy noise and phase and frequency distortions.

Keywords

backpropagation; continuous time systems; delay systems; feedforward neural nets; multilayer perceptrons; pattern recognition; backpropagation; continuous time delay neural network; continuous time signal; feedforward multilayer neural network; temporal pattern recognition; Delay effects; Feeds; Multi-layer neural network; Neural networks; Noise robustness; Pattern recognition; Phase detection; Phase frequency detector; Phase noise; Testing;

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.2004.1381082

Filename

1381082