Neural networks organizations to learn complex robotic functions

Abstract. This paper considers the general problem of function estimation with a modular approach of neural computing. We propose to use functionally independent subnetworks to learn complex functions. Thus, function approximation is decomposed and amounts to estimate different elementary sub-functions rather than the whole function with a single network. This modular decomposition is a way to introduce some a priori knowledge in neural estimation. Functionally independent subnetworks are obtained with a bidirectional learning scheme. Implemented with self-organizing maps, the modular approach has been applied to a robot control problem, a robot positioning task.

• Type: Conference
• Year: 2003
• Where: ESANN
• Authors: Gilles Hermann, Patrice Wira, Jean-Philippe Urban
• Keywords: ESANN 2003, ESANN 2007, Function Estimation, Independent Subnetworks, Modular Approach