Skip to main content

E-insensitive Unsupervised Learning.

Fyfe, C. and Gabrys, B., 1999. E-insensitive Unsupervised Learning. In: International Conference on Neural Networks and Artificial Intelligence (ICNNAI'99), October 1999, Brest, Belarus, 10-18.

Full text available as:




One of the major paradigms for unsupervised learning in Artificial Neural Networks is Hebbian learning. The standard implementations of Hebbian learning are optimal under the assumptions of Gaussian noise in a data set. We derive e-insensitive Hebbian learning based on minimising the least absolute error in a compressed data set and show that the learning rule is equivalent to the Principal Component Analysis (PCA) networks' learning rules under a variety of conditions.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Science & Technology
ID Code:9641
Deposited By: Professor Bogdan Gabrys LEFT
Deposited On:11 Mar 2009 21:36
Last Modified:14 Mar 2022 13:21


Downloads per month over past year

More statistics for this item...
Repository Staff Only -