Neural network models for combinatorial optimization : a survey of deterministic, stochastic and chaotic approaches

• Autorzy: Smith K. , Potvin J. , Kwok T.
• Języki publikacji: EN

Abstrakty

EN

This paper serves as a tutorial on the use of neural networks for solving combinatorial optimization problems. It reviews the two main classes of neural network models : the gradient-based neural networks such as the Hopfield network, and the deformable template approaches such as the elastic net method and self organizing maps. In each class, the original model is presented, its limitations discussed, and subsequent developments and extensions are reviewed. Particular emphasis is placed on stochastic and chaotic variations on the neural network models designed to improve the optimization performance. Finally, the performance of these neural network models is compared and discussed relative to other heuristic approaches.

Słowa kluczowe

EN

chaos; combinatorial optimization; deformable templates; Hopfield networks; neural networks; self-organizing map

PL

chaos; odwzorowanie samoporządkujące; optymalizacja kombinatoryczna; sieć Hopfielda; sieć neuronowa

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2002
• Tom: Vol. 31, no 2
• Strony: 183--216
• Opis fizyczny: Bibliogr. 87 poz.,Rys., wykr.,

Twórcy

autor

Smith K.

autor

Potvin J.

autor

Kwok T.