We have derived a new algorithm for dictionary learning for sparse coding in the ℓ1 exact sparse framework. The algorithm does not rely on an approximation residual to operate, b...
This paper reports our recent exploration of the layer-by-layer learning strategy for training a multi-layer generative model of patches of speech spectrograms. The top layer of t...
Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, ...
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning...
Shape priors attempt to represent biological variations within a population. When variations are global, Principal Component Analysis (PCA) can be used to learn major modes of vari...
Delphine Nain, Steven Haker, Aaron F. Bobick, Alle...