Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Duval Alexandre"'
Autor:
Klein Colin, Duval Alexandre
Publikováno v:
Belgrade Philosophical Annual, Vol 36, Iss 2, Pp 41-57 (2023)
Nikola Grahek's influential book Feeling Pain and Being in Pain introduced philosophers to the strange phenomenon of pain asymbolia. Subsequent philosophical debate around asymbolia has been partly taxonomic: the deep question is whether it is best u
Externí odkaz:
https://doaj.org/article/ee9e533b4626409990e233290c71e4b5
Autor:
Ramlaoui, Ali, Saulus, Théo, Terver, Basile, Schmidt, Victor, Rolnick, David, Malliaros, Fragkiskos D., Duval, Alexandre
Rapid advancements in machine learning (ML) are transforming materials science by significantly speeding up material property calculations. However, the proliferation of ML approaches has made it challenging for scientists to keep up with the most pr
Externí odkaz:
http://arxiv.org/abs/2407.08313
Autor:
Duval, Alexandre, Mathis, Simon V., Joshi, Chaitanya K., Schmidt, Victor, Miret, Santiago, Malliaros, Fragkiskos D., Cohen, Taco, Liò, Pietro, Bengio, Yoshua, Bronstein, Michael
Recent advances in computational modelling of atomic systems, spanning molecules, proteins, and materials, represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. In these graphs, the geometric attributes transform acco
Externí odkaz:
http://arxiv.org/abs/2312.07511
Autor:
Carbonero, Alvaro, Duval, Alexandre, Schmidt, Victor, Miret, Santiago, Hernandez-Garcia, Alex, Bengio, Yoshua, Rolnick, David
The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorporate the geometric configuration of all atoms. However, in practice not all this information may be readily ava
Externí odkaz:
http://arxiv.org/abs/2310.06682
Autor:
AI4Science, Mila, Hernandez-Garcia, Alex, Duval, Alexandre, Volokhova, Alexandra, Bengio, Yoshua, Sharma, Divya, Carrier, Pierre Luc, Benabed, Yasmine, Koziarski, Michał, Schmidt, Victor
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such as electrocatalysts, super-ionic conductors or photovoltaic materials can have a crucial impact, for instance,
Externí odkaz:
http://arxiv.org/abs/2310.04925
Autor:
Duval, Alexandre, Schmidt, Victor, Garcia, Alex Hernandez, Miret, Santiago, Malliaros, Fragkiskos D., Bengio, Yoshua, Rolnick, David
Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetri
Externí odkaz:
http://arxiv.org/abs/2305.05577
Autor:
Duval, Alexandre, Schmidt, Victor, Miret, Santiago, Bengio, Yoshua, Hernández-García, Alex, Rolnick, David
Mitigating the climate crisis requires a rapid transition towards lower-carbon energy. Catalyst materials play a crucial role in the electrochemical reactions involved in numerous industrial processes key to this transition, such as renewable energy
Externí odkaz:
http://arxiv.org/abs/2211.12020
The drone industry is diversifying and the number of pilots increases rapidly. In this context, flight schools need adapted tools to train pilots, most importantly with regard to their own awareness of their physiological and cognitive limits. In civ
Externí odkaz:
http://arxiv.org/abs/2210.14910
Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However, they are n
Externí odkaz:
http://arxiv.org/abs/2209.03473
Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this pa
Externí odkaz:
http://arxiv.org/abs/2104.10482