Title :
A counter-propagation neural network for function approximation
Author :
Lin, Z. ; Khorasani, K. ; Pate, R.V.
Author_Institution :
Dept. of Electr. & Comput. Eng., Concordia Univ., Montreal, Que., Canada
Abstract :
A counterpropagation network architecture for continuous function approximation is introduced. The paradigm consists of a splitting Kohonen layer architecture, functional-link network, continuous activation functions, and a modified training procedure. The network mapping capabilities are analyzed. To demonstrate the applicability of the network, simulation results for the robot inverse kinematic problem are provided. They show an improved function approximation accuracy compared to standard counterpropagation networks
Keywords :
function approximation; mathematics computing; neural nets; parallel architectures; continuous activation functions; counterpropagation network architecture; function approximation; functional-link network; network mapping; neural network; robot inverse kinematic problem; splitting Kohonen layer architecture; training procedure; Computer architecture; Computer networks; Function approximation; Hypercubes; Kinematics; Manipulator dynamics; Neural networks; Neurons; Robots; Statistics;
Conference_Titel :
Systems, Man and Cybernetics, 1990. Conference Proceedings., IEEE International Conference on
Conference_Location :
Los Angeles, CA
Print_ISBN :
0-87942-597-0
DOI :
10.1109/ICSMC.1990.142133
