Simulated Annealing is a meta-heuristic that performs a randomized local search to reach near-optimal solutions of combinatorial as well as continuous optimization problems, In this chapter we show how it can be used to train artificial neural networks by examples. Experimental results indicate that good results can be obtained with little or no tuning.
|Title of host publication||Metaheuristic procedures for training neural networks|
|Place of Publication||Boston, USA|
|Number of pages||16|
|Publication status||Published - 2007|
|Name||Operations Research/Computer Science Interfaces Series|