Accessibility navigation

On simple adaptive momentum

Mitchell, R. J. (2008) On simple adaptive momentum. In: Comley, R. A., Amavasai, B. P., Cheng, X., Ogrady, M., Huyck, C. and Siddique, N. H. (eds.) Proceedings of the 2008 7th IEEE International Conference on Cybernetic Intelligent Systems. IEEE, pp. 215-220. ISBN 9781424429141

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.


Simple Adaptive Momentum [1] was introduced as a simple means of speeding the training of multi-layer perceptrons (MLPs) by changing the momentum term depending on the angle between the current and previous changes in the weights of the MLP. In the original paper. the weight changes of the whole network are used in determining this angle. This paper considers adapting the momentum term using certain subsets of these weights. This idea was inspired by the author's object oriented approach to programming MLPs. successfully used in teaching students: this approach is also described. It is concluded that the angle is best determined using the weight changes in each layer separately.

Item Type:Book or Report Section
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:14435
Uncontrolled Keywords:Neural Networks, Learning Systems, Back propagation, Momentum
Additional Information:Proceedings Paper ID 18 7th IEEE International Conference on Cybernetic Intelligent Systems SEP 09-10, 2008 London, ENGLAND

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation