Unified formulation for training recurrent networks with derivative adaptive critics

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Feldkamp, L.A., Puskorius, G.V., Prokhorov, D.V.
Format: Conference Proceeding
Language:English
Subjects:
Adaptive systems
Area measurement
Backpropagation
Computational intelligence
Dynamic programming
Equations
Laboratories
Learning
Neurodynamics
Programmable control
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
DOI:10.1109/ICNN.1997.614397