Title :
Unified formulation for training recurrent networks with derivative adaptive critics
Author :
Feldkamp, L.A. ; Puskorius, G.V. ; Prokhorov, D.V.
Author_Institution :
Ford Res. Lab., Dearborn, MI, USA
Abstract :
We present a procedure for obtaining the derivatives used in training a recurrent network that combines in a unified framework the techniques of backpropagation through time and derivative adaptive critics. The resulting formulation is consistent with previous descriptions, but has the advantage of allowing the mentioned techniques to be used together in a proportion that is appropriate to a given problem
Keywords :
backpropagation; mathematical programming; recurrent neural nets; backpropagation through time; derivative adaptive critics; dual heuristic programming; learning; recurrent neural networks; Adaptive systems; Area measurement; Backpropagation; Computational intelligence; Dynamic programming; Equations; Laboratories; Learning; Neurodynamics; Programmable control;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614397
