Improving neural network training solutions using regularisation

Neurocomputing

Volumn 37, Issue 1-4, 2001, Pages 71-90

  Mc Loone, Seán ^a   Irwin, George ^a  

^a QUEEN'S UNIVERSITY BELFAST   (United Kingdom)

Author keywords

Neural networks; Regularisation; Training Hybrid optimisation

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; HYBRID; LINEAR SYSTEM; MATHEMATICAL ANALYSIS; NONLINEAR SYSTEM; POSITIVE FEEDBACK; PRIORITY JOURNAL; PROBLEM SOLVING; THEORY; TRAINING;

EID: 0035100447     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(00)00314-3     Document Type: Article

References (33)

1. First - And second-order methods for learning: Between steepest descent and Newton's method
2. BFGS optimization for faster automated supervised learning
3. Curvature-driven smoothing in backpropagation neural networks
4. Improving the generalisation properties of radial basis function neural networks
5. Neurofuzzy modelling approaches in system identification
6. Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks
7. Hybrid learning algorithm for Gaussian potential function networks
8. Improving generalization performance using double backpropagation
9. The cascade-correlation architecture
10. Neural networks and the best approximation property
11. Layered neural networks with Gaussian hidden units as universal approximators
12. Ridge regression: Biased estimation for nonorthogonal problems
13. Optimal brain damage
14. The best approximation properties and error bounds of Gaussian networks
15. Bayesian methods for adaptive models
16. A hybrid linear/nonlinear training algorithm for feedforward neural networks
17. Fast parallel off-line training of multilayer perceptrons
18. Nonlinear optimization of RBF networks
19. Fast gradient based off-line training of multilayer perceptrons
20. A scaled conjugate gradient algorithm for fast supervised learning
21. Regularisation in the selection of radial basis function centres
22. Introduction to radial basis function networks
23. Learning internal representations by error propagation
24. Non-linear system identification with neural networks
25. Overtraining, regularization, and searching for minimum with application to neural networks
26. Minimisation methods for training feedforward neural networks
27. A comparison of nonlinear optimization strategies for feed-forward adaptive layered networks
28. Oscillation-resisting in the learning of backpropagation neural networks