Abstract
Feedforward neural networks (FNNs) have been extensively applied to various areas such as control, system identification, function approximation, pattern recognition etc. A novel robust control approach to the learning problems of FNNs is further investigated in this study in order to develop efficient learning algorithms which can be implemented with optimal parameter settings and considering noise effect in the data. To this aim, the learning problem of a FNN is cast into a robust output feedback control problem of a discrete time-varying linear dynamic system. New robust learning algorithms with adaptive learning rate are therefore developed, using linear matrix inequality (LMI) techniques to find the appropriate learning rates and to guarantee the fast and robust convergence. Theoretical analysis and examples are given to illustrate the theoretical results. © 2012 Elsevier Ltd.
| Original language | English |
|---|---|
| Pages (from-to) | 33-45 |
| Journal | Neural Networks |
| Volume | 31 |
| Online published | 14 Mar 2012 |
| DOIs | |
| Publication status | Published - Jul 2012 |
| Externally published | Yes |
Funding
The author gratefully acknowledges the constructive and helpful comments and suggestions from the anonymous reviewers, and the support of the GRF project of Hong Kong RGC (Ref. 517810), the Department General Research Funds and Internal Competitive Research Grants (B-Q24E, G-YJ13, A-PL07, A-PL74) of Hong Kong Polytechnic University for this work.
Research Keywords
- Feed-forward neural network (FNN)
- Robust learning
- Linear matrix inequality (LMI)
- Robust control approach
- BACKPROPAGATION ALGORITHM