Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data
- 1 March 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 40 (2) , 439-454
- https://doi.org/10.1109/18.312166
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- Projection pursuit learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Exploring Regression Structure Using Nonparametric Functional EstimationJournal of the American Statistical Association, 1993
- Complexity Regularization with Application to Artificial Neural NetworksPublished by Springer Nature ,1991
- Constructive approximations for neural networks by sigmoidal functionsProceedings of the IEEE, 1990
- Investigating Smooth Multiple Regression by the Method of Average DerivativesJournal of the American Statistical Association, 1989
- An Optimal Global Nearest Neighbor MetricIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984
- Parameters for Integrating Periodic Functions of Several VariablesMathematics of Computation, 1983
- Projection Pursuit RegressionJournal of the American Statistical Association, 1981
- Existence of good lattice points in the sense of HlawkaMonatshefte für Mathematik, 1978
- Probability Inequalities for Sums of Bounded Random VariablesJournal of the American Statistical Association, 1963