Cellular SRN Trained by Extended Kalman Filter Shows Promise for ADP
Authors:
- R. IlinRIR. Ilin
- R. KozmaRKR. Kozma
- P.J. WerbosPWP.J. Werbos
- 1 January 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 506-510
Abstract
Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP's, in particular for solving approximate dynamic programming problems. The 2D maze navigation has been considered as a proof-of-concept task. Present work improves the previous results by training the network with extended Kalman filter (EKF). The original EKF algorithm has been slightly modified. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results. The implications of this improvement are discussed.Keywords
This publication has 5 references indexed in Scilit:
- Generalized maze navigation: SRN critics solve what feedforward or Hebbian nets cannot2002
- Kalman Filtering and Neural Networks2001
- The cellular simultaneous recurrent network adaptive critic design for the generalized maze problem has a simple closed-form solution2000
- Adaptive critic designs: A case study for neurocontrolNeural Networks, 1995
- The Physiology of PerceptionScientific American, 1991