Practical methods of optimization; (2nd ed.)
Practical methods of optimization; (2nd ed.)
The cascade-correlation learning architecture
Advances in neural information processing systems 2
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Hybrid Feedforward Neural Networks for Solving Classification Problems
Neural Processing Letters
Variations of the two-spiral task
Connection Science
Hybrid artificial neural networks: models, algorithms and data
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
| Hi-index | 0.00 |
In this study we investigate a hybrid neural network architecture formodelling purposes. The proposed network is based on the multilayerperceptron (MLP) network. However, in addition to the usual hidden layersthe first hidden layer is selected to be a centroid layer. Each unit inthis new layer incorporates a centroid that is located somewhere in theinput space. The output of these units is the Euclidean distance betweenthe centroid and the input. The centroid layer clearly resembles thehidden layer of the radial basis function (RBF) networks. Therefore thecentroid based multilayer perceptron (CMLP) networks can be regarded as ahybrid of MLP and RBF networks. The presented benchmark experiments showthat the proposed hybrid architecture is able to combine the goodproperties of MLP and RBF networks resulting fast and efficient learning,and compact network structure.