Conference
Evolutionary combining of basis function neural networks for classification
| العنوان: | Evolutionary combining of basis function neural networks for classification |
|---|---|
| المؤلفون: | Hervás Martínez, César, Martínez Estudillo, Francisco José, Carbonero Ruz, Mariano, Romero, Cristóbal, Fernández, Juan Carlos |
| سنة النشر: | 2007 |
| الوصف: | The paper describes a methodology for constructing a possible combination of different basis functions (sigmoidal and product) for the hidden layer of a feed forward neural network, where the architecture, weights and node typology are learned based on evolutionary programming. This methodology is tested using simulated Gaussian data set classification problems with different linear correlations between in put variables and different variances. It was found that combined basis functions are the more accurate for classification than pure sigmoidal or product-unit models. Combined basis functions present competitive results which are obtained using linear discriminant analysis, the best classification methodology for Gaussian data sets |
| نوع الوثيقة: | conference object |
| اللغة: | English |
| ردمك: | 978-3-540-73052-1 3-540-73052-4 |
| تدمد: | 0302-9743 |
| Relation: | This work has been financed in part by the TIN2005-08386-C05-02 project of the Spanish Inter-Ministerial Commission of Science and Technology (CICYT) and FEDER funds; Martínez, Cesar & Martínez-Estudillo, Francisco & Carbonero-Ruz, Mariano & Romero, Cristóbal & Fernández, Juan Carlos. (2007). Evolutionary Combining of Basis Function Neural Networks for Classification. 447-456. 10.1007/978-3-540-73053-8_45.; https://hdl.handle.net/20.500.12412/5302; IWINAC 2007. Bio-inspired Modeling of Cognitive Tasks, Second International Work-Conference on the Interplay Between Natural and Artificial Computation |
| DOI: | 10.1007/978-3-540-73053-8_45 |
| الاتاحة: | https://hdl.handle.net/20.500.12412/5302 https://doi.org/10.1007/978-3-540-73053-8_45 |
| Rights: | Attribution-NonCommercial-NoDerivatives 4.0 Internacional ; http://creativecommons.org/licenses/by-nc-nd/4.0/ ; openAccess |
| رقم الانضمام: | edsbas.2AED414 |
| قاعدة البيانات: | BASE |
| ردمك: | 9783540730521 3540730524 |
|---|---|
| تدمد: | 03029743 |
| DOI: | 10.1007/978-3-540-73053-8_45 |