DocumentCode
285267
Title
Nonlinear functional approximation with networks using adaptive neurons
Author
Tawel, Raoul
Author_Institution
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
Volume
3
fYear
1992
fDate
7-11 Jun 1992
Firstpage
491
Abstract
A novel mathematical framework for the rapid learning of nonlinear mappings and topological transformations is presented. It is based on allowing the neuron´s parameters to adapt as a function of learning. This fully recurrent adaptive neuron model has been successfully applied to complex nonlinear function approximation problems such as the highly degenerate inverse kinematics problem in robotics
Keywords
function approximation; learning (artificial intelligence); network topology; neural nets; adaptive neuron model; highly degenerate inverse kinematics problem; learning; network topology; neural nets; nonlinear function approximation; nonlinear mappings; robotics; topological transformations; Adaptive systems; Couplings; Differential equations; Function approximation; Logistics; Microelectronics; Neurons; Propulsion; Space technology; Temperature;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location
Baltimore, MD
Print_ISBN
0-7803-0559-0
Type
conf
DOI
10.1109/IJCNN.1992.227126
Filename
227126
Link To Document