On the properties of periodic perceptrons
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 188-193
- https://doi.org/10.1109/icnn.1997.611662
Abstract
This paper presents a summary of research regarding a modified perceptron model in which processing elements utilize a periodic activation function. Empirical results for a number of benchmark tests provide some indication of the "in practice" power of networks containing periodic processors for pattern classification tasks. In addition, new results are reported in which the internal structure of the network is shown to be interpretable, and indeed provides a basis for rule extraction. Together these results give some indication of the behaviour that can be expected when applying networks containing periodic perceptrons to pattern classification tasks, and provides dimensions along which such processing elements may be distinguished from standard sigmoid devices.Keywords
This publication has 3 references indexed in Scilit:
- On training artificial neural networks to identify periodic functionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Density Plots of Hidden Value Unit Activations Reveal Interpretable BandsConnection Science, 1995
- Modifying the Generalized Delta Rule to Train Networks of Non-monotonic Processors for Pattern ClassificationConnection Science, 1992