no code implementations • NeurIPS 2011 • Arthur D. Szlam, Karol Gregor, Yann L. Cun
This work describes a conceptually simple method for structured sparse coding and dictionary design.
no code implementations • NeurIPS 2010 • Durk P. Kingma, Yann L. Cun
Score Matching is a recently-proposed criterion for training high-dimensional density models for which maximum likelihood training is intractable.
no code implementations • NeurIPS 2010 • Koray Kavukcuoglu, Pierre Sermanet, Y-Lan Boureau, Karol Gregor, Michael Mathieu, Yann L. Cun
We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features.
no code implementations • NeurIPS 2007 • Marc'Aurelio Ranzato, Y-Lan Boureau, Yann L. Cun
Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the raw input.