Cellular SRN Trained by Extended Kalman Filter Shows Promise for ADP

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 prev...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The 2006 IEEE International Joint Conference on Neural Network Proceedings s. 506 - 510
Hlavní autoři: Ilin, R., Kozma, R., Werbos, P.J.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 2006
Témata:
Cellular networks
Convergence
Cost function
Dynamic programming
Electronic mail
Equations
Learning
Navigation
Neural networks
Recurrent neural networks
ISBN:9780780394902, 0780394909
ISSN:2161-4393
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISBN:9780780394902
0780394909
ISSN:2161-4393
DOI:10.1109/IJCNN.2006.246724