I was reading Deep Learning of Representations for Unsupervised and Transfer Learning, and they state the following:
They have only a small number of unlabeled examples (4096) and very few labeled examples (1 to 64 per class) available to a Hebbian linear classifier (which discriminates according to the median between the centroids of two classes compared) applied separately to each class against the others.
I have searched about what a Hebbian linear classifier is, but I couldn't find more than an explanation about what Hebbian learning is, so can anybody explain what Hebbian linear classifier is?
