Title :
An incremental growing neural network and its application to robot control
Author :
Carlevarino, A. ; Martinotti, R. ; Metta, G. ; Sandini, G.
Author_Institution :
Lira Lab., Genova Univ., Italy
Abstract :
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
Keywords :
neurocontrollers; performance evaluation; robots; self-organising feature maps; unsupervised learning; GNG-Soft networks; Growing Neural Gas; SoftMax function network; approximation error; approximation requests; incremental growing neural network; network growth rate; performance; robot control; self-tuning neural models; unsupervised learning; Approximation error; Context modeling; Electronic mail; Frequency estimation; Inverse problems; Low pass filters; Network topology; Neural networks; Orbital robotics; Robot control;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861486
