Networks of exponential neurons for multivariate function approximation
作者： S. Geva , J. Sitte
DOI: 10.1109/IJCNN.1991.170732
关键词: Algorithm 、 Artificial intelligence 、 Function approximation 、 Pattern recognition 、 Mathematics 、 Artificial neural network 、 Sigmoid function 、 Activation function 、 Radial basis function network 、 Multilayer perceptron 、 Backpropagation 、 Feedforward neural network
摘要: A three-layer neural network, having a hidden layer of neurons with an exponential transfer function, capable performing function approximation more accurately, and economically, than conventional multilayer perceptron (MLP) sigmoidal is described. The network was trained by variation the standard backpropagation gradient-descent technique. results difficult problem, where MLP similar size simply fails to perform within reasonable constraints on training time, are shown graphically. >
sci-hub.se 参考文章(8)
Fernando M. Silva, Luis B. Almeida, Speeding up Backpropagation Advanced Neural Computers. pp. 151- 158 ,(1990) , 10.1016/B978-0-444-88400-8.50022-4
S. Geva, J. Sitte, G. Finn, Pattern classification by an exponental response neural net hawaii international conference on system sciences. pp. 290- 297 ,(1991) , 10.1109/HICSS.1991.183897
Donald F. Specht, Probabilistic neural networks Neural Networks. ,vol. 3, pp. 109- 118 ,(1990) , 10.1016/0893-6080(90)90049-Q
P. Hart, The condensed nearest neighbor rule (Corresp.) IEEE Transactions on Information Theory. ,vol. 14, pp. 515- 516 ,(1968) , 10.1109/TIT.1968.1054155
Sukhan Lee, Rhee M. Kil, A Gaussian potential function network with hierarchically self-organizing learning Neural Networks. ,vol. 4, pp. 207- 224 ,(1991) , 10.1016/0893-6080(91)90005-P
T. Poggio, F. Girosi, Networks for approximation and learning Proceedings of the IEEE. ,vol. 78, pp. 1481- 1497 ,(1990) , 10.1109/5.58326
T.-D. Chiueh, R.M. Goodman, Recurrent correlation associative memories IEEE Transactions on Neural Networks. ,vol. 2, pp. 275- 284 ,(1991) , 10.1109/72.80338
S. Chen, C.F.N. Cowan, P.M. Grant, Orthogonal least squares learning algorithm for radial basis function networks IEEE Transactions on Neural Networks. ,vol. 2, pp. 302- 309 ,(1991) , 10.1109/72.80341