Associative memories for chemical sensing

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 ha...

Full description

Saved in:
Bibliographic Details
Main Authors: Reznik, A.M., Shirshov, Yu.M., Snopok, B.A., Nowicki, D.W., Dekhtyarenko, A.K., Kruglenko, I.V.
Format: Conference Proceeding
Language:English
Subjects:
Associative memory
Chemical sensors
Feedforward neural networks
Image recognition
Kinetic theory
Neural networks
Physics
Resonance
Sensor arrays
Sensor phenomena and characterization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
DOI:10.1109/ICONIP.2002.1201972