Abstract

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.

Document Downloads