Home  |   Login  |   Logout  |   Access Information  |   Alerts  |   Purchase History  |   Cart  |   Sitemap  |   Help   
 
CrossRef Search
BROWSE SEARCH IEEE XPLORE GUIDE SUPPORT
You requested this document:
1. Hidden partitioning of a visual feedback-based neuro-controller
Urban, J.P.; Buessler, J.L.; Gresser, J.;
Knowledge-Based Intelligent Electronic Systems, 1998. Proceedings KES '98. 1998 Second International Conference on
Volume 3,  21-23 April 1998 Page(s):53 - 60 vol.3
Abstract:

Robotic controllers take advantage from neural network learning capabilities as long as the dimensionality of the problem is kept moderate. The paper explores the possibilities offered by the combination of several neural networks to design more complex modular controllers. This modularity is based on an internal partitioning of the problem. The partitioning must remain hidden, and should not affect the controller's interface or functioning, including during its adaptation phases. We introduce a bi-directional architecture to derive the learning rules of the modules. The neuro-controller is trained globally, based on the interactions of the system with its environment, as one would do for a single network. The approach is illustrated on a robotic reaching application. Several partitioning variants of the neuro-controller are discussed and compared
Abstract | Full Text: PDF(804 KB)    IEEE CNF
 
» Key
IEEE JNL IEEE Journal or Magazine
IEE JNL IEE Journal or Magazine
IEEE CNF IEEE Conference Proceeding
IEE CNF IEE Conference Proceeding
IEEE STD IEEE Standard
 
 
Indexed by IEE Inspec
© Copyright 2008 IEEE – All Rights Reserved