Hybrid neural networks: An evolutionary approach with local search

Integrated Computer-Aided Engineering

Volumn 9, Issue 1, 2002, Pages 57-72

  Iyoda, Eduardo Masato ^a   Von Zuben, Fernando J ^a  

^a UNIVERSITY OF CAMPINAS   (Brazil)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION THEORY; GENETIC ALGORITHMS; LEARNING ALGORITHMS; MULTILAYER NEURAL NETWORKS; OPTIMIZATION;

HYBRID NEURAL NETWORKS;

FEEDFORWARD NEURAL NETWORKS;

EID: 0036142879     PISSN: 10692509     EISSN: None     Source Type: Journal    
DOI: 10.3233/ica-2002-9104     Document Type: Article

References (26)

1. On a class of efficient learning algorithms for neural networks
2. What size net gives valid generalization?
3. Universal approximation bounds for superpositions of a sigmoidal function
4. Approximation by superposition of a sigmoidal function
5. Optimal nonlinear approximation
6. The cascade-correlation learning architecture
7. Projection pursuit regression
8. Statistical estimation of the number of hidden units for feedforward neural networks
9. On the approximate realization of continuous mappings by neural networks
10. Regularization theory and neural networks architectures
11. Multilayer feedforward neural networks are universal approximators
12. Regression modelling in back-propagation and projection pursuit learning
13. Evolutionary hybrid composition of activation functions in feedforward neural networks
14. Constructive feedforward neural networks for regression problems: A survey
15. Use of bias term in projection pursuit learning improves approximation and convergence properties
16. A scaled conjugate gradient algorithm for fast supervised learning
17. Uniform crossover in genetic algorithms
18. Unit-growing learning optimizing the solvability condition for model-free regression
19. Projection pursuit and the solvability condition applied to constructive learning
20. No free lunch theorems for optimization