On the selection of hidden neurons with heuristic search strategies for approximation

Abstract. Feature Selection techniques usually follow some search strategy to select a suitable subset from a set of features. Most neural network growing algorithms perform a search with Forward Selection with the objective of nding a reasonably good subset of neurons. Using this link between both elds (feature selection and neuron selection), we propose and analyze di erent algorithms for the construction of neural networks based on heuristic search strategies coming from the feature selection eld. The results of an experimental comparison to Forward Selection using both synthetic and real data show that a much better approximation can be achieved, though at the expense of a higher computational cost.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Ignacio Barrio, Enrique Romero, Lluís A. Belanche Muñoz
• Keywords: ESANN 2006, ESANN 2007, Feature Selection, Feature Selection Techniques, Forward Selection