State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer

Thu Jun 13th 06:30 -- 09:00 PM @ Pacific Ballroom #1

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as state reification, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing toward this distribution. Our intuition is that if the network can remain in a familiar manifold of hidden space, subsequent layers of the net should be well trained to respond appropriately. We show that this state-reification method helps neural nets to generalize better, especially when labeled data are sparse, and also helps overcome the challenge of achieving robust generalization with adversarial training.

Author Information

Alex Lamb (Universite de Montreal)
Jonathan Binas (Mila, Montreal)
Parth Goyal (Université de Montréal)
Sandeep Subramanian (MILA)
Ioannis Mitliagkas (MILA, UdeM)
Yoshua Bengio (Mila / U. Montreal)

Yoshua Bengio (PhD'1991 in Computer Science, McGill University). After two post-doctoral years, one at MIT with Michael Jordan and one at AT&T Bell Laboratories with Yann LeCun, he became professor at the department of computer science and operations research at Université de Montréal. Author of two books (a third is in preparation) and more than 200 publications, he is among the most cited Canadian computer scientists and is or has been associate editor of the top journals in machine learning and neural networks. Since '2000 he holds a Canada Research Chair in Statistical Learning Algorithms, since '2006 an NSERC Chair, since '2005 his is a Senior Fellow of the Canadian Institute for Advanced Research and since 2014 he co-directs its program focused on deep learning. He is on the board of the NIPS foundation and has been program chair and general chair for NIPS. He has co-organized the Learning Workshop for 14 years and co-created the International Conference on Learning Representations. His interests are centered around a quest for AI through machine learning, and include fundamental questions on deep learning, representation learning, the geometry of generalization in high-dimensional spaces, manifold learning and biologically inspired learning algorithms.

Mike Mozer (Google Research & U. Colorado Boulder)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors