Washington / DC / San Francisco / P. Gradient / Aberystwyth / London / /
Company
Neural Networks / Cox / MIT Press / R. Deconvolutional Networks / Convolutional Networks / /
Country
United States / United Kingdom / / /
Facility
Courant Institute of Mathematical Sciences / New York University / /
IndustryTerm
stage systems / filter bank / segmentation algorithms / coordinate descent algorithm / energy function / iterative shrinkage-thresholding algorithm / stochastic online procedure / deep belief networks / object recognition systems / matrix-vector product / proposed sparse modeling systems / energy-based model / real world applications / recent systems / dot product / Online dictionary learning / sparse coding algorithm / initialized systems / shrinkage operator / supervised learning algorithms / unsupervised trained systems / online updates / recognition systems / energy / steepest descent algorithm / /
NaturalFeature
Integral channel / /
Organization
Laboratoire d’Informatique de l’Ecole Normale Sup´erieure / Society of Photo-Optical Instrumentation Engineers / New York University / MIT / US Federal Reserve / IEEE Computer Society / Courant Institute of Mathematical Sciences / /
Learning Convolutional Feature Hierarchies for Visual Recognition Koray Kavukcuoglu1 , Pierre Sermanet1 , Y-Lan Boureau2,1 , Karol Gregor1 , Micha¨el Mathieu1 , Yann LeCun1 1