| Title | Classification by means of evolutionary product-unit neural networks |
|---|---|
| Authors | Hervás C. , MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ, Gutiérrez P.A. |
| External publication | No |
| Means | IEEE Int. Conf. Neural. Netw. Conf. Proc. |
| Scope | Conference Paper |
| Nature | Científica |
| SJR Impact | 0.202 |
| Web | https://www.scopus.com/inward/record.uri?eid=2-s2.0-40649104792&doi=10.1109%2fijcnn.2006.246614&partnerID=40&md5=9851842c51a286e42d548c63382dbfa9 |
| Publication date | 01/01/2006 |
| Scopus Id | 2-s2.0-40649104792 |
| DOI | 10.1109/ijcnn.2006.246614 |
| Abstract | We propose a classification method based on a special class of feed-forward neural network, namely product-unit neural networks. They are based on multiplicative nodes instead of additive ones, where the nonlinear basis functions express the possible strong interactions among the variables. We apply an evolutionary algorithm to determine the basic structure of the productunit model and to estimate the coefficients of the model. The empirical results show that the proposed model is very promising in terms of classification accuracy, yielding a stateof-the-art performance. © 2006 IEEE. |
| Keywords | Evolutionary algorithms; Feedforward neural networks; Mathematical models; Multiplicative nodes; Nonlinear basis functions; Product unit model; Classification (of information) |
| Universidad Loyola members |