no code implementations • ACL 2020 • Jacob Russin, Jason Jo, R O{'}Reilly, all, Yoshua Bengio
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution.
1 code implementation • 12 Feb 2020 • Giulia Zarpellon, Jason Jo, Andrea Lodi, Yoshua Bengio
We aim instead at learning a policy that generalizes across heterogeneous MILPs: our main hypothesis is that parameterizing the state of the B&B search tree can aid this type of generalization.
1 code implementation • 22 Apr 2019 • Jake Russin, Jason Jo, Randall C. O'Reilly, Yoshua Bengio
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution.
no code implementations • 18 Jun 2018 • Jason Jo, Vikas Verma, Yoshua Bengio
We focus on two supervised visual reasoning tasks whose labels encode a semantic relational rule between two or more objects in an image: the MNIST Parity task and the colorized Pentomino task.
no code implementations • 17 Dec 2017 • Matteo Fischetti, Jason Jo
A commonly-used nonlinear operator is the so-called rectified linear unit (ReLU), whose output is just the maximum between its input value and zero.
1 code implementation • 30 Nov 2017 • Jason Jo, Yoshua Bengio
The goal of this article is to measure the tendency of CNNs to learn surface statistical regularities of the dataset.
no code implementations • 31 Dec 2014 • Jason Jo
These numerical experiments show that for a variety of easily computable empirical weights, weighted nuclear norm minimization outperforms unweighted nuclear norm minimization in the non-uniform sampling regime.