City Research Online

Abstract

We derive an algorithm to exactly calculate the mixed second-order derivatives of a neural network's output with respect to its input vector and weight vector. This is necessary for the adaptive dynamic programming (ADP) algorithms globalized dual heuristic programming (GDHP) and value-gradient learning. The algorithm calculates the inner product of this second-order matrix with a given fixed vector in a time that is linear in the number of weights in the neural network. We use a “forward accumulation” of the derivative calculations which produces a much more elegant and easy-to-implement solution than has previously been published for this task. In doing so, the algorithm makes GDHP simple to implement and efficient, bridging the gap between the widely used DHP and GDHP ADP methods.

Publication Type:	Article
Additional Information:	(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Publisher Keywords:	Neural Networks, Adaptive Dynamic Programming, Dual Heuristic Programming
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology > Computer Science
Related URLs:	Author
SWORD Depositor:	Symplectic Administrator

Export

Downloads