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

Abstract: 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...