Associative memories for chemical sensing

Author

Reznik, A.M. ; Shirshov, Yu.M. ; Snopok, B.A. ; Nowicki, D.W. ; Dekhtyarenko, A.K. ; Kruglenko, I.V.

Volume

5

fYear

2002

fDate

18-22 Nov. 2002

Firstpage

2630

Abstract

We consider application of neural associative memories to chemical image recognition. Chemical image recognition is identification of substance using chemical sensors´ data. The primary advantage of associative memories as compared with feed-forward neural networks is high-speed learning. We have made experiments on odour recognition using hetero-associative and modular auto-associative memories. We have also tested backpropagation NNs with one hidden layer. Associative memories displayed recognition quality not worse than backpropagation networks.

Keywords

content-addressable storage; gas sensors; intelligent sensors; iterative methods; learning (artificial intelligence); pattern recognition; QCM-based arrays; artificial nose; backpropagation networks; chemical image recognition; chemical sensing; fast learning; feedforward neural networks; hetero-associative memories; high-speed learning; maximum classification quality; modular auto-associative memories; neural associative memories; neural software package; odour recognition; single iteration; substance identification; Associative memory; Chemical sensors; Feedforward neural networks; Image recognition; Kinetic theory; Neural networks; Physics; Resonance; Sensor arrays; Sensor phenomena and characterization;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

Print_ISBN

981-04-7524-1

Type

conf

DOI

10.1109/ICONIP.2002.1201972

Filename

1201972