Zobrazeno 1 - 10
of 2 291
pro vyhledávání: '"SCHNEIDER, FRANK"'
Autor:
Lutz, Sarah, Schneider, Frank M., Reich, Sabine, Schimmel, Michelle, Oechler, Hannah, Beinlich, Laura
Being socially excluded seriously threatens individuals’ need to belong and emotional well-being. This article investigates to what extent different coping strategies help overcome these detrimental effects: thinking about real-life friends/enemies
Efficiently learning a sequence of related tasks, such as in continual learning, poses a significant challenge for neural nets due to the delicate trade-off between catastrophic forgetting and loss of plasticity. We address this challenge with a grou
Externí odkaz:
http://arxiv.org/abs/2410.06800
Autor:
Schneider, Frank
Für die Frage nach Kontakten zwischen Musikwissenschaftlern aus Ost und West kann man von der grundlegenden Beobachtung ausgehen, dass während der Jahrzehnte des ‚Kalten Krieges‘ trotz der beiden politisch sich feindlich gegenüberstehenden Lag
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A70714
https://ul.qucosa.de/api/qucosa%3A70714/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A70714/attachment/ATT-0/
The core components of many modern neural network architectures, such as transformers, convolutional, or graph neural networks, can be expressed as linear layers with $\textit{weight-sharing}$. Kronecker-Factored Approximate Curvature (K-FAC), a seco
Externí odkaz:
http://arxiv.org/abs/2311.00636
Bayesian Generalized Linear Models (GLMs) define a flexible probabilistic framework to model categorical, ordinal and continuous data, and are widely used in practice. However, exact inference in GLMs is prohibitively expensive for large datasets, th
Externí odkaz:
http://arxiv.org/abs/2310.20285
Autor:
Dahl, George E., Schneider, Frank, Nado, Zachary, Agarwal, Naman, Sastry, Chandramouli Shama, Hennig, Philipp, Medapati, Sourabh, Eschenhagen, Runa, Kasimbeg, Priya, Suo, Daniel, Bae, Juhan, Gilmer, Justin, Peirson, Abel L., Khan, Bilal, Anil, Rohan, Rabbat, Mike, Krishnan, Shankar, Snider, Daniel, Amid, Ehsan, Chen, Kongtao, Maddison, Chris J., Vasudev, Rakshith, Badura, Michal, Garg, Ankush, Mattson, Peter
Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workloads (e.g., better update rules, tuning protocols, learning rate sched
Externí odkaz:
http://arxiv.org/abs/2306.07179