Nonlinear feature extraction using a neuro genetic hybrid

Feature extraction is a process that extracts salient features from observed variables. It is considered a promising alternative to overcome the problems of weight and structure optimization in artificial neural networks. There were many nonlinear feature extraction methods using neural networks but they still have the same difficulties arisen from the fixed network topology. In this paper, we propose a novel combination of genetic algorithm and feedforward neural networks for nonlinear feature extraction. The genetic algorithm evolves the feature space by utilizing characteristics of hidden neurons. It improved remarkably the performance of neural networks on a number of real world regression and classification problems. Categories and Subject Descriptors I.5.1 [Computing Methodologies]: Pattern Recognition— Models General Terms Performance Keywords Function approximation, neuro-genetic hybrid, feature extraction

• Type: Conference
• Year: 2005
• Where: GECCO
• Authors: Yung-Keun Kwon, Byung Ro Moon
• Keywords: Feature Extraction, GECCO 2005, Neural Networks, Nonlinear Feature Extraction