Modified Hebbian learning for curve and surface fitting
作者： Lei Xu , Erkki Oja , Ching Y. Suen
DOI: 10.1016/0893-6080(92)90006-5
关键词: Noise 、 Artificial neural network 、 Curve fitting 、 Learning rule 、 Hebbian theory 、 Minor (linear algebra) 、 Outlier 、 Mathematics 、 Calculus 、 Principal component analysis 、 Algorithm
摘要: Abstract A linear neural unit with a modified anti-Hebbian learning rule is shown to be able optimally fit curves, surfaces, and hypersurfaces by adaptively extracting the minor component (i.e., counterpart of principal component) input data set. The analyzed mathematically. results computer simulations are given illustrate that this fitting method considerably outperform commonly used least square in resisting both normal noise outlier.
elsevier.com
sci-hub.se 参考文章(20)
J. Rubner, K. Schulten, Development of feature detectors by self-organization Biological Cybernetics. ,vol. 62, pp. 193- 199 ,(1990) , 10.1007/BF00198094
S.Y. Kung, Constrained principal component analysis via an orthogonal learning network international symposium on circuits and systems. ,vol. 1, pp. 719- 722 ,(1990) , 10.1109/ISCAS.1990.112180
Herbert Robbins, Sutton Monro, A Stochastic Approximation Method Annals of Mathematical Statistics. ,vol. 22, pp. 400- 407 ,(1951) , 10.1214/AOMS/1177729586
Foldiak, None, Adaptive network for optimal linear feature extraction international joint conference on neural network. pp. 401- 405 ,(1989) , 10.1109/IJCNN.1989.118615
Erkki Oja, None, NEURAL NETWORKS, PRINCIPAL COMPONENTS, AND SUBSPACES International Journal of Neural Systems. ,vol. 01, pp. 61- 68 ,(1989) , 10.1142/S0129065789000475
J Rubner, P Tavan, A self-organizing network for principal-component analysis EPL. ,vol. 10, pp. 693- 698 ,(1989) , 10.1209/0295-5075/10/7/015
Erkki Oja, Juha Karhunen, On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix Journal of Mathematical Analysis and Applications. ,vol. 106, pp. 69- 84 ,(1985) , 10.1016/0022-247X(85)90131-3
Chauvin, Principal component analysis by gradient descent on a constrained linear Hebbian cell international joint conference on neural network. pp. 373- 380 ,(1989) , 10.1109/IJCNN.1989.118611
C. Lee Giles, Tom Maxwell, Learning, invariance, and generalization in high-order neural networks Applied Optics. ,vol. 26, pp. 4972- 4978 ,(1987) , 10.1364/AO.26.004972
Pierre Baldi, Kurt Hornik, Neural networks and principal component analysis: learning from examples without local minima Neural Networks. ,vol. 2, pp. 53- 58 ,(1989) , 10.1016/0893-6080(89)90014-2