Sliding mode algorithm for training multilayerartificial neural networks
- 8 January 1998
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 34 (1) , 97-98
- https://doi.org/10.1049/el:19980062
Abstract
On-line learning algorithms for artificial neural networks (ANNs) are expected to adapt network parameters in order to face new control situations. A new on-line learning algorithm, based on sliding mode control (SMC) is presented. The results show that ANN inherits some of the advantages of SMC: high speed of learning and robustness.Keywords
This publication has 2 references indexed in Scilit:
- Adaptive control of a class of nonlinear discrete-time systems using neural networksIEEE Transactions on Automatic Control, 1995
- Learning representations by back-propagating errorsNature, 1986