Picture for R Devon Hjelm

R Devon Hjelm

Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

Oct 22, 2020
Tristan Sylvain, Linda Petrini, R Devon Hjelm

Figure 1 for Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

Figure 2 for Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations

* ICML 2019 Workshop on Understanding and Improving General-ization in Deep Learning, Long Beach, California, 2019 Spotlight presentation. arXiv admin note: text overlap with arXiv:1912.12179

Access Paper or Ask Questions

Implicit Regularization in Deep Learning: A View from Function Space

Aug 03, 2020
Aristide Baratin, Thomas George, César Laurent, R Devon Hjelm, Guillaume Lajoie, Pascal Vincent, Simon Lacoste-Julien

Figure 1 for Implicit Regularization in Deep Learning: A View from Function Space

Figure 2 for Implicit Regularization in Deep Learning: A View from Function Space

Figure 3 for Implicit Regularization in Deep Learning: A View from Function Space

Figure 4 for Implicit Regularization in Deep Learning: A View from Function Space

* 24 pages. A preliminary version of this work has been presented at the NeurIPS 2019 Workshops on "Machine Learning with Guarantees" and "Science meets Engineering of Deep Learning"

Access Paper or Ask Questions

Representation Learning with Video Deep InfoMax

Jul 28, 2020
R Devon Hjelm, Philip Bachman

Figure 1 for Representation Learning with Video Deep InfoMax

Figure 2 for Representation Learning with Video Deep InfoMax

Figure 3 for Representation Learning with Video Deep InfoMax

Figure 4 for Representation Learning with Video Deep InfoMax

Access Paper or Ask Questions

Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Jul 12, 2020
Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, Philip Bachman

Figure 1 for Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Figure 2 for Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Figure 3 for Data-Efficient Reinforcement Learning with Momentum Predictive Representations

Figure 4 for Data-Efficient Reinforcement Learning with Momentum Predictive Representations

* The first two authors contributed equally to this work

Access Paper or Ask Questions