multilayer perceptron


Also found in: Acronyms.

multilayer perceptron

A network composed of more than one layer of neurons, with some or all of the outputs of each layer connected to one or more of the inputs of another layer. The first layer is called the input layer, the last one is the output layer, and in between there may be one or more hidden layers.
Mentioned in ?
References in periodicals archive ?
Multilayer perceptron, fuzzy sets, and classification.
Multilayer Perceptron Networks (MLP Networks) and Radial Basis Function Networks (RBF networks) are the two popular methods of feed forward neural network.
The artificial neural network (ANN) developed to simulate the precipitation of the sprinkler was a multilayer perceptron (MLP) model and the best topology was composed of 4 neurons in the input layer, only one hidden layer with 280 neurons and output layer with 256 neurons.
The classifier is used are multilayer perceptron which is also referred as FFBPN.
For classification we used four class multilayer perceptron training pair-wise misclassification cost specific loss function, where in the output layer instead of minimizing the class specific weights [w.
The aim of this paper is to compare the accuracy of DAN2, ARCH and multilayer perceptron neural network models when the volatility of a benchmark return series is forecasted.
Multilayer Perceptron, however, weights of neuron synapses in hidden layer are changed with Finite Impulse Response filters or Lattice-Ladder filters, correspondingly.
The findings from this study are consistent with that of Heazlewood and Keshishian (2010), suggesting that neural networks, specifically the multilayer perceptron (MLP) networks, are more effective in predicting group membership, and displayed higher predictive validity when compared to discriminant analysis.
There are several issues involved in the proposed designing and training of the multilayer perceptron network, such as, selecting how many hidden layers to use in the network; deciding how many neurons to use in each hidden layer; finding a global optimal solution that avoids local minima; converging to an optimal solution in a reasonable period of time; and validating the neural network to test for overfitting.
The models analyzed are: the Multilayer Perceptron (MLP), Radial Basis Function (RBF), Generalized Regression Neural Network (GRNN) and Recurrent Neural Networks (RNN).
Se evaluaron tres (3) modelos de clasificacion: Naive Bayes (NB), arbol de decision con algoritmo J48 y red neuronal Multilayer Perceptron (RN).
Among their topics are detecting defects in composite materials, using outlier analysis and multilayer perceptron neural networks to identify and localize damage in plastic composite plates reinforced with carbon fibers, predicting fatigue life, optimizing the neural network prediction of composite fatigue life under variable amplitude loading using Bayesian regularization, and determining initial design parameters by using genetically optimized neural network systems.

Full browser ?