Hi Gang, Today we will have a our new post-doc, Heng Luo, tell us about his previous work. Looking forward to seeing you all there. When: Today, 15h00 Where: LISA Lab (AA3256) Title: "Learning Class-relevant Features and Class-irrelevant Features via a Hybrid third-order RBM". Abstract: Restricted Boltzmann Machines are commonly used in unsupervised learning to extract features from training data. Since these features are learned for regenerating training data a classifier based on them has to be trained. If only a few of the learned features are discriminative other non-discriminative features will distract the classifier during the training process and thus waste computing resources for testing. In this paper, we present a hybrid third-order Restricted Boltzmann Machine in which class-relevant features (for recognizing) and class-irrelevant features (for generating only) are learned simultaneously. As the classification task uses only the class-relevant features, the test itself becomes very fast. We show that class-irrelevant features help class-relevant features to focus on the recognition task and introduce useful regularization effects to reduce the norms of class-relevant features. Thus there is no need to use weight-decay for the parameters of this model. Experiments on the MNIST, NORB and Caltech101 Silhouettes data sets show very promising results. If time permits, I will also briefly discuss my paper, "Sparse Group Restricted Boltzmann Machines". Cheers, Aaron -- Aaron C. Courville Département d’Informatique et de recherche opérationnelle Université de Montréal email:Aaron.Courville@gmail.com
Afficher les réponses par date
participants (1)
-
Aaron Courville