A sequential algorithm for feed-forward neural networks with optimal coefficients and interacting frequencies

Authors:
Enrique Romero;René Alquézar
Affiliations:
Departament de Llenguatges i Sistemes Informítics, Universitat Politècnica de Catalunya, Barcelona, Spain;Departament de Llenguatges i Sistemes Informítics, Universitat Politècnica de Catalunya, Barcelona, Spain
Venue:
Neurocomputing
Year:
2006

Citing 27
Cited 4

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The cascade-correlation learning architecture

Advances in neural information processing systems 2
A resource-allocating network for function interpolation

Neural Computation
Neural networks and the bias/variance dilemma

Neural Computation
Dynamic node architecture learning: an information theoretic approach

Neural Networks
A procedure for determining the topology of multilayer feedforward neural networks

Neural Networks
A function estimation approach to sequential learning with neural networks

Neural Computation
Approximation and Estimation Bounds for Artificial Neural Networks

Machine Learning - Special issue on computational learning theory
Signal representation using adaptive normalized Gaussian functions

Signal Processing
The nature of statistical learning theory

The nature of statistical learning theory
A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Investigation of the CasCor family of learning algorithms

Neural Networks
Modeling with constructive backpropagation

Neural Networks
A new algorithm to design compact two-hidden-layer artificial neural networks

Neural Networks
Kernel Matching Pursuit

Machine Learning
New training strategies for constructive neural networks with application to regression problems

Neural Networks
Predictive models for the breeder genetic algorithm i. continuous parameter optimization

Evolutionary Computation
Matching pursuits with time-frequency dictionaries

IEEE Transactions on Signal Processing
Universal approximation bounds for superpositions of a sigmoidal function

IEEE Transactions on Information Theory
Constructive algorithms for structure learning in feedforward neural networks for regression problems

IEEE Transactions on Neural Networks
Objective functions for training new hidden units in constructive neural networks

IEEE Transactions on Neural Networks
Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks

IEEE Transactions on Neural Networks
Exploring constructive cascade networks

IEEE Transactions on Neural Networks
Orthogonal least squares learning algorithm for radial basis function networks

IEEE Transactions on Neural Networks
Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks

IEEE Transactions on Neural Networks
Regression modeling in back-propagation and projection pursuit learning

IEEE Transactions on Neural Networks
Ridge polynomial networks

IEEE Transactions on Neural Networks

Heuristics for the selection of weights in sequential feed-forward neural networks: An experimental study

Neurocomputing
An experimental study on methods for the selection of basis functions in regression

Neurocomputing
Comparing error minimized extreme learning machines and support vector sequential feed-forward neural networks

Neural Networks
Comparing support vector machines and feed-forward neural networks with similar parameters

IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning

Quantified Score

Hi-index	0.01

Visualization

Abstract

An algorithm for sequential approximation with optimal coefficients and interacting frequencies (SAOCIF) for feed-forward neural networks is presented. SAOCIF combines two key ideas. The first one is the optimization of the coefficients (the linear part of the approximation). The second one is the strategy to choose the frequencies (the non-linear weights), taking into account the interactions with the previously selected ones. The resulting method combines the locality of sequential approximations, where only one frequency is found at every step, with the globality of non-sequential methods, where every frequency interacts with the others. The idea behind SAOCIF can be theoretically extended to general Hilbert spaces. Experimental results show a very satisfactory performance.