Skip to Main content Skip to Navigation
Conference papers

Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers

Abstract : This paper presents an application of the biologically realistic JASTAP neural network model to classification tasks. The JASTAP neural network model is presented as an alternative to the basic multi-layer perceptron model. An evolutionary procedure previously applied to the simultaneous solution of feature selection and neural network training on standard multi-layer perceptrons is extended with JASTAP model. Preliminary results on IRIS standard data set give evidence that this extension allows the use of smaller neural networks that can handle noisier data without any degradation in classification accuracy.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00643498
Contributor : Michal Valko <>
Submitted on : Tuesday, November 22, 2011 - 10:09:43 AM
Last modification on : Tuesday, June 29, 2021 - 12:20:08 PM
Long-term archiving on: : Friday, November 16, 2012 - 11:40:38 AM

File

VMC05.pdf
Files produced by the author(s)

Identifiers

Citation

Michal Valko, Nuno Cavalheiro, Marco Castelani. Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers. Proceedings of 2005 Portuguese Conference on Artificial Intelligence, Dec 2005, Covilha, Portugal. pp.181-187, ⟨10.1109/EPIA.2005.341291⟩. ⟨hal-00643498⟩

Share

Metrics

Record views

204

Files downloads

749