An Incremental Growing Neural Network and its Application to Robot Control

This paper describes a novel network model, which is able to control its growth on the basis of the approximation requests. Two classes of self-tuning neural models are considered; namely Growing Neural Gas (GNG) and SoftMax function networks. We combined the two models into a new one: hence the name GNG-Soft networks. The resulting model is characterized by the effectiveness of the GNG in distributing the units within the input space and the approximation properties of SoftMax functions. We devised a method to estimate the approximation error in an incremental fashion. This measure has been used to tune the network growth rate. Results showing the performance of the network in a real-world robotic experiment are reported.

• Type: Conference
• Year: 2000
• Where: IJCNN
• Authors: A. Carlevarino, R. Martinotti, Giorgio Metta, Giulio Sandini
• Keywords: Approximation, IJCNN 2000, Neural Networks, Self-tuning Neural Models, Softmax Functions