A neural network to solve discrete dynamic programming problems

An artificial neural network to solve discrete dynamic programming problems is proposed. This approach presents some advantages with regard to alternative approaches because of the inherent parallelism of the neural networks. Some important applications are addressed to illustrate the usefulness of...

Full description

Saved in:
Bibliographic Details
Published inIEEE International Conference on Neural Networks pp. 1433 - 1438 vol.3
Main Authors Francelin, R.A., Gomide, F.A.C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1993
Subjects
Artificial neural networks
Constraint optimization
Dynamic programming
Network topology
Neural network hardware
Neural networks
Neurofeedback
Neurons
Parallel processing
Performance analysis
Online AccessGet full text

Cover

More Information
Summary:An artificial neural network to solve discrete dynamic programming problems is proposed. This approach presents some advantages with regard to alternative approaches because of the inherent parallelism of the neural networks. Some important applications are addressed to illustrate the usefulness of the approach proposed. An algorithm for dynamic programming neural network (DPNN) implementation and an equivalence between the DPNN and the dynamic programming procedure are presented.< >
ISBN:0780309995
9780780309999
DOI:10.1109/ICNN.1993.298767