Canonical dual solutions to nonconvex radial basis neural network optimization problem

Authors:
Vittorio Latorre;David Yang Gao
Affiliations:
-;-
Venue:
Neurocomputing
Year:
2014

Citing 12
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Global Continuation for Distance Geometry Problems

SIAM Journal on Optimization
Canonical Dual Transformation Method and Generalized Triality Theory in Nonsmooth Global Optimization*

Journal of Global Optimization
Convergent Decomposition Techniques for Training RBF Neural Networks

Neural Computation
Real time face and mouth recognition using radial basis function neural networks

Expert Systems with Applications: An International Journal
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Prediction of Parkinson's disease tremor onset using radial basis function neural networks

Expert Systems with Applications: An International Journal
On the versatility of radial basis function neural networks: A case study in the field of intrusion detection

Information Sciences: an International Journal
A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design

The Journal of Machine Learning Research
Forecasting stock indices using radial basis function neural networks optimized by artificial fish swarm algorithm

Knowledge-Based Systems
Face recognition with radial basis function (RBF) neural networks

IEEE Transactions on Neural Networks
Canonical dual approach to solving the maximum cut problem

Journal of Global Optimization

Quantified Score

Hi-index	0.01

Visualization

Abstract

Radial Basis Functions Neural Networks (RBFNNs) are tools widely used in regression problems. One of their principal drawbacks is that the formulation corresponding to the training with the supervision of both the centers and the weights is a highly non-convex optimization problem, which leads to some fundamental difficulties for the traditional optimization theory and methods. This paper presents a generalized canonical duality theory for solving this challenging problem. We demonstrate that by using sequential canonical dual transformations, the nonconvex optimization problem of the RBFNN can be reformulated as a canonical dual problem (without duality gap). Both global optimal solution and local extrema can be classified. Several applications to one of the most used Radial Basis Functions, the Gaussian function, are illustrated. Our results show that even for a one-dimensional case, the global minimizer of the nonconvex problem may not be the best solution to the RBFNNs, and the canonical dual theory is a promising tool for solving general neural networks training problems.