Zobrazeno 1 - 5
of 5
pro vyhledávání: '"L��tjens, Bj��rn"'
Autor:
Lacoste, Alexandre, Sherwin, Evan David, Kerner, Hannah, Alemohammad, Hamed, L��tjens, Bj��rn, Irvin, Jeremy, Dao, David, Chang, Alex, Gunturkun, Mehmet, Drouin, Alexandre, Rodriguez, Pau, Vazquez, David
Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downstream tasks. Such models, recently coined as foundation models, have be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff8ffadacb2aa1da2e7d467e9ccf3270
http://arxiv.org/abs/2112.00570
http://arxiv.org/abs/2112.00570
Autor:
Cachay, Salva R��hling, Erickson, Emma, Bucker, Arthur Fender C., Pokropek, Ernest, Potosnak, Willa, Bire, Suyash, Osei, Salomey, L��tjens, Bj��rn
Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Ni��o-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16e7076855b53c582135e3675a9ffe32
Autor:
Cachay, Salva R��hling, Erickson, Emma, Bucker, Arthur Fender C., Pokropek, Ernest, Potosnak, Willa, Osei, Salomey, L��tjens, Bj��rn
Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Ni��o-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f68f7b69ac652db3bddc74ebc6c7631f
An increasing amount of companies and cities plan to become CO2-neutral, which requires them to invest in renewable energies and carbon emission offsetting solutions. One of the cheapest carbon offsetting solutions is preventing deforestation in deve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66b4849c0c7dc2157db4f9d4495c3f9a
http://arxiv.org/abs/1912.07850
http://arxiv.org/abs/1912.07850
Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs (from nois
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::236b5dcd70843c49fad24fa12dcadfe7
http://arxiv.org/abs/1910.12908
http://arxiv.org/abs/1910.12908