Neural network controller using autotuning method for nonlinear functions
Authors:
- 1 July 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 3 (4) , 595-601
Abstract
An autotuning method for the optimum sigmoid function of neural networks is proposed. It is based on the steepest descent method. Simulated results using a learning-type direct controller confirm both the practicality and the characteristics of the autotuning method.Keywords
This publication has 4 references indexed in Scilit:
- Some Remarks on Characteristics of Direct Neuro-Controller with Regard to Adaptive ControlTransactions of the Society of Instrument and Control Engineers, 1991
- Force control of robot manipulator by neural network. (Control of one degree-of-freedom manipulator).Journal of the Robotics Society of Japan, 1989
- Generic constraints on underspecified target trajectories1989
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988