Abstract. We propose a method of unsupervised learning from stationary, vector-valued processes. A low-dimensional subspace is selected on the basis of a criterion which rewards da...
In contrast to the equivalence of linear blind source separation and linear independent component analysis it is not possible to recover the original source signal from some unkno...
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...
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists...
Marc'Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau,...