An Extension of ε-Insensitive Hebbian Learning to Form a Non-Interfering Basis.

  1. Fyfe, Colin 1
  2. Corchado, Emilio 1
  1. 1 Applied Computational Intelligence Research Unit, The University of Paisley, Scotland
Revue:
International Journal of Computational Intelligence and Applications

ISSN: 1469-0268,  1757-5885

Année de publication: 2003

Volumen: 03

Número: 03

Pages: 281-296

Type: Article

DOI: 10.1142/S1469026803001002 GOOGLE SCHOLAR

D'autres publications dans: International Journal of Computational Intelligence and Applications

Résumé

We review an extension of Hebbian learning which has been called ε-Insensitive Hebbian Learning (Fyfe and MacDonald, 2001) and derive lateral connections from a probability density function. We use these lateral connections to move outputs towards the mode of the pdf and use the resulting outputs to train the feedforward connections. We show that the resulting network is able to identify a single orientation of bars from a mixture of horizontal and vertical bars.

Références bibliographiques

  • Fyfe C., Neuro Comput.
  • 10.1142/S0129065789000475
  • 10.1088/0954-898X_7_2_006
  • 10.1088/0954-898X_9_2_002
  • 10.1016/S0893-6080(05)80107-8
  • Bishop C. M., (1995), Neural Networks for Pattern Recognition
  • 10.1016/0893-6080(94)90060-4
  • Seung H. S., Adv. Neural Inf. Process. Syst., 10
  • Bertsekas D. P., (1995), Nonlinear Programming
  • 10.1023/A:1009606706736