Metaheuristic design of feedforward neural networks
Citations
248 citations
224 citations
187 citations
151 citations
110 citations
References
[...]
46,982 citations
41,772 citations
37,861 citations
"Metaheuristic design of feedforward..." refers background in this paper
...Many other ANN models, like radial basis function [23] and support vector machine [24] are a special class of three-layer FNNs....
[...]
35,161 citations
"Metaheuristic design of feedforward..." refers methods in this paper
...Similarly, a PSO and SA based hybrid algorithm for optimizing FNN were proposed in [191], where, in each iteration, each PSO particle was governed by SA metropolis criteria [100] that determined global best particle for PSO algorithm....
[...]
...It uses Monte Carlo method [100] to determine the acceptance probability of a newly generated solution in the neighborhood of the current solution....
[...]
28,888 citations
"Metaheuristic design of feedforward..." refers background or methods in this paper
...Many researchers suggested that the Levenberg-Marquardt (LM) method outperforms BP, CG, and Quasi-Newton methods [79, 80]....
[...]
...Similar to the CG, many other variants of derivative-based conventional methods are used for weights optimization: Quasi-Newton [65], Gauss-Newton [76], or Levenberg-Marquardt [77]....
[...]
...problem, which suggests to using the sum of squared error (4) [77]....
[...]