Classification method for multiclass classification in a layered neural network and method-based neural network

作者: Jean-Pierre Nadal , Jacques-Ariel Sirat

DOI:

关键词:

摘要: Method comprising learning steps in the course of which at least one layer is constructed by addition successive neurons necessary for implementing, dichotomies, classification examples distributed classes. In order to create from a group over more than two classes, each neuron tends distinguish its input data according sub-groups predetermined classes particular said neuron, an analysis into principal components distribution subjected question. …

参考文章(4)
Koutsougeras, Papachristou, Training of a neural network for pattern classification based on an entropy measure IEEE 1988 International Conference on Neural Networks. pp. 247- 254 ,(1988) , 10.1109/ICNN.1988.23854
M Mezard, Jean-P Nadal, Learning in feedforward layered networks: the tiling algorithm Journal of Physics A. ,vol. 22, pp. 2191- 2203 ,(1989) , 10.1088/0305-4470/22/12/019
J A Sirat, J-P Nadal, Neural trees: a new tool for classification Network: Computation In Neural Systems. ,vol. 1, pp. 423- 438 ,(1990) , 10.1088/0954-898X_1_4_003