Picture for David Rolnick

David Rolnick

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

May 23, 2023
Qidong Yang, Alex Hernandez-Garcia, Paula Harder, Venkatesh Ramesh, Prasanna Sattegeri, Daniela Szwarcman, Campbell D. Watson, David Rolnick

* Presented at the ICLR 2023 workshop on "Tackling Climate Change with Machine Learning"

Access Paper or Ask Questions

Bird Distribution Modelling using Remote Sensing and Citizen Science data

May 01, 2023
Mélisande Teng, Amna Elmustafa, Benjamin Akera, Hugo Larochelle, David Rolnick

Figure 1 for Bird Distribution Modelling using Remote Sensing and Citizen Science data

Figure 2 for Bird Distribution Modelling using Remote Sensing and Citizen Science data

Figure 3 for Bird Distribution Modelling using Remote Sensing and Citizen Science data

Figure 4 for Bird Distribution Modelling using Remote Sensing and Citizen Science data

* Tackling Climate Change with Machine Learning Workshop, 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda

Access Paper or Ask Questions

FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Apr 28, 2023
Alexandre Duval, Victor Schmidt, Alex Hernandez Garcia, Santiago Miret, Fragkiskos D. Malliaros, Yoshua Bengio, David Rolnick

Figure 1 for FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Figure 2 for FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Figure 3 for FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Figure 4 for FAENet: Frame Averaging Equivariant GNN for Materials Modeling

* Accepted at ICML 2023

Access Paper or Ask Questions

PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design

Nov 22, 2022
Alexandre Duval, Victor Schmidt, Santiago Miret, Yoshua Bengio, Alex Hernández-García, David Rolnick

Figure 1 for PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design

Figure 2 for PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design

Figure 3 for PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design

Figure 4 for PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design

* Accepted at the NeurIPS 2022 AI for Accelerated Materials Design Workshop

Access Paper or Ask Questions

Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Oct 24, 2022
Setareh Cohen, Nam Hee Kim, David Rolnick, Michiel van de Panne

Figure 1 for Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Figure 2 for Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Figure 3 for Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Figure 4 for Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

* NeurIPS 2022 camera ready

Access Paper or Ask Questions

Bugs in the Data: How ImageNet Misrepresents Biodiversity

Aug 24, 2022
Alexandra Sasha Luccioni, David Rolnick

Figure 1 for Bugs in the Data: How ImageNet Misrepresents Biodiversity

Figure 2 for Bugs in the Data: How ImageNet Misrepresents Biodiversity

Figure 3 for Bugs in the Data: How ImageNet Misrepresents Biodiversity

Figure 4 for Bugs in the Data: How ImageNet Misrepresents Biodiversity

Access Paper or Ask Questions