Regularising neural networks using flexible multivariate activation function
Authors:
- 31 March 2004
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 17 (2) , 247-260
Abstract
No abstract availableKeywords
This publication has 16 references indexed in Scilit:
- Multilayer feedforward networks with adaptive spline activation functionIEEE Transactions on Neural Networks, 1999
- Splines: a perfect fit for signal and image processingIEEE Signal Processing Magazine, 1999
- Complex-valued neural networks with adaptive spline activation function for digital-radio-links nonlinear equalizationIEEE Transactions on Signal Processing, 1999
- Regression modeling in back-propagation and projection pursuit learningIEEE Transactions on Neural Networks, 1994
- A universal theorem on learning curvesNeural Networks, 1993
- Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theoryNeural Networks, 1991
- Approximation of functions on a compact set by finite sums of a sigmoid function without scalingNeural Networks, 1991
- A data predistortion technique with memory for QAM radio systemsIEEE Transactions on Communications, 1991
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- On the structure of continuous functions of several variablesTransactions of the American Mathematical Society, 1965