@inproceedings{eed1e3ae3a104fb78948a64d3c2c88cc,
title = "Evolutionary Feature Selection for Artificial Neural Network Pattern Classifiers",
abstract = "This paper presents FeaSANNT, an evolutionary procedure for feature selection and weight training for neural network classifiers. FeaSANNT exploits the global nature of evolutionary search to avoid sub-optimal peaks of performance. FeaSANNT was used to train a multi-layer perceptron classifier on seven benchmark problems. FeaSANNT attained accurate and consistent learning results, and significantly reduced the number of data attributes compared to four state-of-the-art standard filter and wrapper feature selection methods. Thanks to the robustness of evolutionary search, FeaSANNT did not require time-consuming re-tuning of the learning parameters for each test problem.",
author = "Duc Pham and Marco Castellani and AA Fahmy",
year = "2009",
month = jan,
day = "1",
doi = "10.1109/INDIN.2009.5195881",
language = "English",
isbn = "978-1-4244-3759-7",
series = "IEEE International Conference on Industrial Informatics",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
pages = "658--663",
booktitle = "Industrial Informatics, 2009. INDIN 2009. 7th IEEE International Conference on",
note = "IEEE International Conference on Industrial Informatics (INDIN) ; Conference date: 01-01-2009",
}