Efficient training procedures for adaptive kernel classifiers
作者： S.V. Chakravarthy , J. Ghosh , L. Deuser , S. Beck
关键词:
摘要: The authors investigate two training schemes for adapting the locations and receptive field widths of centroids in radial basis function classifiers. adaptive kernel classifier is able to adjust responses hidden units during using an extension Delta rule, thus leading improved performance reduced network size. rapid classifier, on other hand, uses faster learned vector quantization algorithm adapt centroids. This shows a remarkable reduction time with little compromise accuracy. these networks evaluated underwater acoustic transient signals. >
sci-hub.se 参考文章(16)
David Lowe, David S. Broomhead, Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks Complex Systems. ,vol. 2, pp. 321- 355 ,(1988)
Kohonen, Barna, Chrisley, Statistical pattern recognition with neural networks: benchmarking studies IEEE 1988 International Conference on Neural Networks. pp. 61- 68 ,(1988) , 10.1109/ICNN.1988.23829
Lee Sukhan, Kil, Multilayer feedforward potential function network IEEE 1988 International Conference on Neural Networks. pp. 161- 171 ,(1988) , 10.1109/ICNN.1988.23844
H. Ritter, K. Schulten, On the stationary state of Kohonen's self-organizing sensory mapping Biological Cybernetics. ,vol. 54, pp. 99- 106 ,(1986) , 10.1007/BF00320480
Teuvo Kohonen, Self-Organization and Associative Memory ,(1984)
R.P. Lippmann, Pattern classification using neural networks IEEE Communications Magazine. ,vol. 27, pp. 47- 50 ,(1989) , 10.1109/35.41401
Mahesan Niranjan, Frank Fallside, Neural networks and radial basis functions in classifying static speech patterns Computer Speech & Language. ,vol. 4, pp. 275- 289 ,(1990) , 10.1016/0885-2308(90)90009-U
Eric J. Hartman, James D. Keeler, Jacek M. Kowalski, Layered neural networks with Gaussian hidden units as universal approximations Neural Computation. ,vol. 2, pp. 210- 215 ,(1990) , 10.1162/NECO.1990.2.2.210
T. Poggio, F. Girosi, Regularization algorithms for learning that are equivalent to multilayer networks. Science. ,vol. 247, pp. 978- 982 ,(1990) , 10.1126/SCIENCE.247.4945.978
J. Park, I. W. Sandberg, Universal approximation using radial-basis-function networks Neural Computation. ,vol. 3, pp. 246- 257 ,(1991) , 10.1162/NECO.1991.3.2.246