Multilayer perceptron neural networks to compute quasistatic parameters of asymmetric coplanar waveguides
Citations
75 citations
68 citations
63 citations
Cites background from "Multilayer perceptron neural networ..."
...An important class of ANNs is the multilayer perceptron (MLP) [21], which is suitable for modeling high-dimensional and highly nonlinear problems....
[...]
...An important class of ANNs is the multilayer perceptron (MLP) [21], which is suitable for modeling...
[...]
...The success of MLPs for a particular problem depends on the adequacy of the training algorithm regarding the necessities of the problem....
[...]
...An MLP consists of three types of layers: an input layer, an output layer and one or more hidden layers....
[...]
...In the study, the well-known Levenberg-Marquardt (LM) algorithm [22] is adopted to train the MLPs for obtaining high-precision synthesis models....
[...]
54 citations
31 citations
References
29,130 citations
"Multilayer perceptron neural networ..." refers methods in this paper
...of training algorithms used to train a MLPNN and a frequently used one is called the BP training algorithm [1,4,17]....
[...]
23,814 citations
"Multilayer perceptron neural networ..." refers background in this paper
...Therefore, a lot of variations to improve the convergence of the BP were proposed such as DBD, EDBD, QP [6,19,24,27]....
[...]
6,899 citations
"Multilayer perceptron neural networ..." refers background in this paper
...(23), Jk is the Jacobian of g(wk) evaluated by taking derivative of g(wk) with respect to wk , % is the Marquardt parameter, I is the identity matrix [8,13,30]....
[...]
...In particular, it generally does not su=er from the problem of slow convergence [8,13,30]....
[...]
2,622 citations
"Multilayer perceptron neural networ..." refers methods in this paper
...of training algorithms used to train a MLPNN and a frequently used one is called the BP training algorithm [1,4,17]....
[...]
2,254 citations