An improved method using radial basis function neural networks to speed up optimization algorithms

IEEE Transactions on Magnetics

Volumn 38, Issue 2 I, 2002, Pages 1081-1084

  Bazan, Marek ^a   Aleksa, Martin ^b   Russenschuck, Stephan ^b  

^a UNIVERSITY OF WROC AW   (Poland)

^b CERN   (Switzerland)

Author keywords

Function approximation; Optimization; Radial basis function neural networks

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; OPTIMIZATION; RADIAL BASIS FUNCTION NETWORKS; REGRESSION ANALYSIS; VECTORS;

SEARCH ALGORITHMS;

SUPERCONDUCTING MAGNETS;

EID: 0036493749     PISSN: 00189464     EISSN: None     Source Type: Journal    
DOI: 10.1109/20.996277     Document Type: Article

References (12)

1. A multiquadratics based algorithm for the acceleration of simulated annealing optimization procedures
2. Adaptive coupling of differential evolution and multiquadratics approximation for the tuning of the optimization process
3. A combined method for global optimization using radial basis function and deterministic approach
4. Using neural networks to speed up optimization algorithms
5. Interpolation of scattered data: Distance matrices and conditionally positive definite functions
6. Layered neural networks with Gaussian hidden units as universal approximations
7. Generalized cross-validation as a method for choosing a good ridge parameter
8. Fast learning in networks of locally-tuned processing units