Title :
Nonlinear functional approximation with networks using adaptive neurons
Author_Institution :
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
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;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227126
