A simplification of the backpropagation-through-time algorithm for optimal neurocontrol

Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPT...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on neural networks Ročník 8; číslo 2; s. 437 - 441
Hlavní autori: Bersini, H., Gorrini, V.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York, NY IEEE 01.03.1997
Institute of Electrical and Electronics Engineers
Predmet:
Applied sciences
Artificial intelligence
Backpropagation algorithms
Bioreactors
Calculus
Computer science; control theory; systems
Connectionism. Neural networks
Dynamic programming
Equations
Exact sciences and technology
Jacobian matrices
Lagrangian functions
Multi-layer neural network
Neural networks
Optimal control
State feedback
Backpropagation algorithm
Experimental result
Optimal control
Dynamic programming
Neural network
Optimization
Multilayer network
ISSN:1045-9227, 1941-0093
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor.
Bibliografia:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1045-9227
1941-0093
DOI:10.1109/72.557698