Hopfield neural networks for timetabling: formulations, methods, and comparative results
Computers and Industrial Engineering - Special issue: Focussed issue on applied meta-heuristics
Microprocessors & Microsystems
Fast hopfield neural networks using subspace projections
Neurocomputing
FPGA prototyping of neuro-adaptive decoder
CIMMACS '10 Proceedings of the 9th WSEAS international conference on computational intelligence, man-machine systems and cybernetics
Hi-index | 0.00 |
This paper discusses the implementation of Hopfield neural networks for solving constraint satisfaction problems using Field Programmable Gate Arrays (FPGAs). It discusses techniques for formulating such problems as discrete neural networks, and then it describes the N-Queen problem using this formulation. A prototype implementation of the a number of different N-Queen problems is described and results are presented that illustrate that a speedup of up to 3 orders of magnitude is possible using current FPGAs devices