Search For:

Displaying 1-4 out of 4 total
Guest Editors' Introduction: Special Section on Learning Deep Architectures
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Samy Bengio,Li Deng,Hugo Larochelle,Honglak Lee,Ruslan Salakhutdinov
Issue Date:August 2013
pp. 1795-1797
There has been a resurgence of research in the design of deep architecture models and learning algorithms, i.e., methods that rely on the extraction of a multilayer representation of the data. Often referred to as deep learning, this topic of research has ...
Learning to rank by aggregating expert preferences
Found in: Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM '12)
By Hugo Larochelle, Maksims N. Volkovs, Richard S. Zemel
Issue Date:October 2012
pp. 843-851
We present a general treatment of the problem of aggregating preferences from several experts into a consensus ranking, in the context where information about a target ranking is available. Specifically, we describe how such problems can be converted into ...
Extracting and composing robust features with denoising autoencoders
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By Hugo Larochelle, Pascal Vincent, Pierre-Antoine Manzagol, Yoshua Bengio
Issue Date:July 2008
pp. 1096-1103
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training pr...
Classification using discriminative restricted Boltzmann machines
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By Hugo Larochelle, Yoshua Bengio
Issue Date:July 2008
pp. 536-543
Recently, many applications for Restricted Boltzmann Machines (RBMs) have been developed for a large variety of learning problems. However, RBMs are usually used as feature extractors for another learning algorithm or to provide a good initialization for d...