Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Koker, Teddy"'
Autor:
Gao, Shanghua, Koker, Teddy, Queen, Owen, Hartvigsen, Thomas, Tsiligkaridis, Theodoros, Zitnik, Marinka
Advances in time series models are driving a shift from conventional deep learning methods to pre-trained foundational models. While pre-trained transformers and reprogrammed text-based LLMs report state-of-the-art results, the best-performing archit
Externí odkaz:
http://arxiv.org/abs/2403.00131
The calculation of electron density distribution using density functional theory (DFT) in materials and molecules is central to the study of their quantum and macro-scale properties, yet accurate and efficient calculation remains a long-standing chal
Externí odkaz:
http://arxiv.org/abs/2312.05388
Autor:
Queen, Owen, Hartvigsen, Thomas, Koker, Teddy, He, Huan, Tsiligkaridis, Theodoros, Zitnik, Marinka
Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to an interpretable temporal pattern. While explainers from other modalit
Externí odkaz:
http://arxiv.org/abs/2306.02109
Autor:
He, Huan, Queen, Owen, Koker, Teddy, Cuevas, Consuelo, Tsiligkaridis, Theodoros, Zitnik, Marinka
Unsupervised domain adaptation (UDA) enables the transfer of models trained on source domains to unlabeled target domains. However, transferring complex time series models presents challenges due to the dynamic temporal structure variations across do
Externí odkaz:
http://arxiv.org/abs/2302.03133
Recent work has shown the potential of graph neural networks to efficiently predict material properties, enabling high-throughput screening of materials. Training these models, however, often requires large quantities of labelled data, obtained via c
Externí odkaz:
http://arxiv.org/abs/2211.13408
Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single input that pre
Externí odkaz:
http://arxiv.org/abs/2107.12329
Deep Neural Networks (DNNs) are widely used for decision making in a myriad of critical applications, ranging from medical to societal and even judicial. Given the importance of these decisions, it is crucial for us to be able to interpret these mode
Externí odkaz:
http://arxiv.org/abs/2101.05791
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.