Mean field annealing

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Mean field annealing is a deterministic approximation to the simulated annealing technique of solving optimization problems.[1] This method uses mean field theory and is based on Peierls' inequality.

References[edit]

  1. ^ Bilbro, G.L.; Snyder, W.E. ; Garnier, S.J. ; Gault, J.W. (Jan 1992). "Mean field annealing: a formalism for constructing GNC-like algorithms". IEEE Transactions on Neural Networks 3 (1): 131 – 138. doi:10.1109/72.105426.