Title :
Training of a three-layer dynamical recurrent neural network for nonlinear input-output mapping
Author :
Sudharsanan, S.I. ; Sundareshan, M.K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Arizona Univ., Tucson, AZ, USA
Abstract :
A three-layer dynamical neural network with feedback and recurrent connections is proposed for nonlinear input-output mapping applications. A simple-to-implement distributed learning scheme is developed, and convergence properties of the training procedure are established. Application of the network architecture and the learning scheme to the identification of the dynamics of a nonlinear system is made, and a performance evaluation is given
Keywords :
feedback; learning systems; neural nets; convergence; feedback; nonlinear input-output mapping; nonlinear input-output mapping applications; simple-to-implement distributed learning scheme; three-layer dynamical recurrent neural network; Application software; Backpropagation; Convergence; Multi-layer neural network; Neural networks; Neurofeedback; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Signal processing algorithms;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155322
