1995 IEEE International Conference on Neural Networks: Proceedings, the University of Western Australia, Perth, Western Australia, 27 November-1 December 1995, Volume 2 |
Contents
NEURAL NETWORK INFORMATION CRITERION FOR THE OPTIMAL NUMBER | 655 |
ON THE EFFECT OF THE NONLINEARITY OF THE SIGMOID FUNCTION | 668 |
APPLICATIONS 3 | 686 |
Copyright | |
13 other sections not shown
Other editions - View all
Common terms and phrases
adaptive analysis applications approach approximation architecture Artificial Neural Networks Australia backpropagation Black-Scholes BP network calculated CFCT classification computational convergence defined detection distribution dynamic equation error estimation evaluation expert system fault filter forecasting function fuzzy rules genetic algorithm global harmonic hidden layer hidden nodes hidden units hybrid IEEE IEEE Trans implementation initial input layer input patterns input vector iterations Japan Kohonen learning algorithm learning rate linear mapping matrix memory method minimal multilayer perceptron neural net neuro-fuzzy neuron noise nonlinear obtained operator optimal output layer paper parallel parameters perceptron performance power system prediction problem processor projection pursuit proposed quantization recurrent neural networks represents samples selected sensor shown in Figure signal simulation Table techniques Technology tion topology training data training patterns training set University unsupervised learning update values variables vector quantization waveforms weights