A novel digital neural network for the travelling salesman problem

In this paper, we present a novel neural network solution to the Travelling Salesperson's Problem. In comparison to the Hopfield Neural Network for the task, the proposed network requires N neurons and O(N/sup 2/) weights to solve a N-city instance. The proposed network is entirely digital, and...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:ICONIP '02 : proceedings of the 9th International Conference on Neural Information Processing : computational intelligence for the E-age : November 18-22, 2002, Singapore Ročník 3; s. 1320 - 1324 vol.3
Hlavní autoři: Varma, A., Jayadeva
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 2002
Témata:
Cities and towns
Costs
Field programmable analog arrays
Field programmable gate arrays
Hardware
Hopfield neural networks
Neural networks
Neurons
Phased arrays
Traveling salesman problems
ISBN:9810475241, 9789810475246
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we present a novel neural network solution to the Travelling Salesperson's Problem. In comparison to the Hopfield Neural Network for the task, the proposed network requires N neurons and O(N/sup 2/) weights to solve a N-city instance. The proposed network is entirely digital, and has been mapped onto a Field Programmable Gate Array. Initial results are encouraging and the FPGA takes under 20 microseconds to solve the task for chosen examples. The re-programmable nature of the FPGA makes the proposed approach a very low cost, reusable hardware approach.
ISBN:9810475241
9789810475246
DOI:10.1109/ICONIP.2002.1202835