In high dimensional data sets not all dimensions contain an equal amount of information and most of the time global features are more important than local differences. This makes ...
Humans can recognize biological motion from strongly impoverished stimuli, like point-light displays. Although the neural mechanism underlying this robust perceptual process have n...
Rodrigo Sigala, Thomas Serre, Tomaso Poggio, Marti...
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...
In this paper, we compare case-based spam filters, focusing on their resilience to concept drift. In particular, we evaluate how to track concept drift using a case-based spam fi...
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...