Successive approximation training algorithm for feedforward neural networks

Neurocomputing

Volumn 42, Issue 1-4, 2002, Pages 311-322

  Liang, Y C ^a,b   Feng, D P ^a   Lee, H P ^b   Lim, S P ^b   Lee, K H ^b  

^a JILIN UNIVERSITY   (China)

^b NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Convergence analysis; Error estimate; Generalization performance; Phase training; Successive approximation training

Indexed keywords

APPROXIMATION THEORY; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; LEARNING ALGORITHMS;

SUCCESSIVE APPROXIMATION TRAINING ALGORITHMS;

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; ANALYSIS; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; ERROR; EXPERIMENT; LETTER; PERFORMANCE; PRIORITY JOURNAL; STAGING; THEORY; TRAINING;

EID: 0036131765     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(01)00576-8     Document Type: Article

References (19)

1. Advances and problems in the study of multilayer feedforward neural networks
2. Theory of back-propagation neural networks
3. Fast learning method for back-propagation neural network by evolutionary adaptation of learning rates
4. Identification of nonlinear characteristics in cushioning packaging using genetic evolutionary neural networks
5. Identification of nonlinearities in cushioning packaging using neural networks with fuzzy adaptive control
6. A study of identification of nonlinear characteristics in cushioning packaging based on neural networks
7. Application of fuzzy neural networks to the prediction of time series
8. Application of neural networks to identification of nonlinear characteristics in cushioning packaging
9. Advances in identification of nonlinear characteristics of packaging based on computational intelligence
10. Identification of restoring forces in nonlinear vibration systems based on neural networks
11. An efficient EM-based training algorithm for feedforward neural networks
12. Fast convergent generalized back-propagation algorithm with constant learning rate
13. Several realistic approaches to improve the generalization of feedforward neural networks
14. When networks disagree: Ensemble methods for hybrid neural networks
15. Fast training of multilayer perceptrons
16. A new kind of neuron model with a tunable activation function and its applications
17. Some views on the research of multilayer feedforward neural networks
18. Researches on fault tolerance of feedforward neural networks-status and prospects
19. On the BP algorithm of feedforward neural networks