Hi Gang,
Today we have a special NIPS preview. Lab members have volunteered to
give 5 minute spotlight talks on a NIPS2010 talk in which they are
interested.
Date and Time: Today, Thursday Dec. 2nd, 14h30
Location: LISA lab, AA3256
Speakers and Titles:
Ian Tiled Convolutional Neural Networks
Olivier Over-complete representations on recurrent neural networks can
support persistent percepts
Salah Sparse Coding for Learning Interpretable Spatio-Temporal Primitives
Dumitru Label Embedding Trees for Large Multi-Class Tasks
Grégoire Regularized estimation of image statistics by score matching
Pierre-Antoine t-logistic regression
Arnaud Learning Convolutional Features Hierarchies for Visual Recognition
David Hallucinations in Charles Bonnet Syndrome Induced by
Homeostasis: a Deep Boltzmann Machine Model
Guillaume Improving the Asymptotic Performance of MCMC by Inserting
Vortices OR Short-term memory in neuronal networks through dynamical
compressed sensing
Xavier G. An analysis on negative curvature induced by singularity in
multi-layer neural-network learning (not sure yet)
Cheers,
Aaron
--
Aaron C. Courville
Département d’Informatique et
de recherche opérationnelle
Université de Montréal
email:Aaron.Courville@gmail.com