DocumentCode :
2871052
Title :
On the solutions of one-class-one-outputed feedforward neural network classifiers using backpropagation training
Author :
Huang, De-Shuang
Author_Institution :
Beijing Inst. of Syst. Eng., China
Volume :
2
fYear :
1998
fDate :
1998
Firstpage :
1301
Abstract :
This paper studies the solutions of the outer-supervised batch-style learning based one-class-one-outputed (OCOO) feedforward neural network (FNN) classifiers. It is proven that if the condition of the hidden neuron number is greater than the total training sample number, which is sufficient but not necessary, is satisfied, the network would uniquely converge to the global minima with null costs, and that the condition of the range space of the outer-supervised signal matrix being included in the range space of the hidden output matrix is a sufficient and necessary condition of ensuring local free minima. Furthermore, in the case of the hidden neuron number being smaller than the total training sample number and greater than the output neuron number, it is shown that the global minimum solutions with null costs may also be derived by adequately adjusting the first layer weights. In the case of the hidden neuron number being smaller than the output neuron number, however, it is shown that there would not exist any global minima with null costs in the error surface
Keywords :
backpropagation; convergence; feedforward neural nets; learning (artificial intelligence); pattern classification; backpropagation training; error surface; feedforward neural network classifiers; first layer weight; global minima; hidden neuron number; hidden output matrix; null costs; one-class-one-outputed neural network; outer-supervised batch-style learning; outer-supervised signal matrix; output neurons; range space; total training sample number; Backpropagation; Cost function; Feedforward neural networks; Least squares methods; Neural networks; Neurons; Resonance light scattering; Sufficient conditions; Systems engineering and theory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4325-5
Type :
conf
DOI :
10.1109/ICOSP.1998.770858
Filename :
770858
Link To Document :
بازگشت