An on-line hybrid learning algorithm for multilayer perceptron in identification problems

Computers and Electrical Engineering

Volumn 28, Issue 6, 2002, Pages 587-598

  Sha, Daohang ^a   Baji, Vladimir B ^a  

^a DURBAN UNIVERSITY OF TECHNOLOGY   (South Africa)

Author keywords

Gradient descent method; Hybrid learning; Neural networks; Recursive least squares parameter estimation; Soft computing

Indexed keywords

GRADIENT METHODS; LEARNING ALGORITHMS; LEAST SQUARES APPROXIMATIONS; PARAMETER ESTIMATION; RECURSIVE FUNCTIONS;

MULTILAYER PERCEPTRONS;

MULTILAYER NEURAL NETWORKS;

EID: 0036832924     PISSN: 00457906     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0045-7906(00)00063-X     Document Type: Article

References (31)

1. 30 Years of adaptive neural networks: Perceptron, madaline, and backpropagation
2. Comparison of optimized backpropagation algorithms
3. Advanced supervised learning in multi-layer perceptrons - From backpropagation to adaptive learning algorithms
4. Accelerated learning in back-propagation nets
5. Towards faster stochastic gradient search
6. Learning rate schedules for faster stochastic gradient search
7. Using curvature information for fast stochastic search
8. On-line step size adaptation
9. Adaptive on-line ANN learning algorithm and application to identification of non-linear systems
10. Fast training algorithms for multilayer neural mets
11. Training feedforward networks with Marquardt algorithm
12. A generalized learning paradigm exploiting the structure of feedforward neural networks
13. A fast multilayer neural networks training algorithm based on the layer-by-layer optimizing procedures
14. Extended least squares based algorithm for training feedforward networks
15. An accelerated learning algorithm for multilayer perceptrons: Optimization layer by layer
16. A new error function at hidden layers for fast training of multilayer perceptrons
17. Modified extended Kalman filtering for supervised learning
18. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter
19. Optimal filtering algorithms for fast learning in feedforward neural networks
20. A fast U-D factorization - Based learning algorithm with applications to nonlinear system modeling and identification
21. Fuzzy modeling using generalized neural networks and Kalman filter algorithm
22. ANFIS: Adaptive-network-based fuzzy inference system
23. On-line hybrid learning algorithm for MLP: Gradient descent and RLS
24. Identification and control of dynamical systems using neural networks
25. Neural networks for identification of nonlinear systems under random piecewise polynomial disturbances
26. A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction