Zobrazeno 1 - 10
of 2 291
pro vyhledávání: '"Schneider Frank"'
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
Publikováno v:
Foundations of Computing and Decision Sciences, Vol 42, Iss 3, Pp 275-295 (2017)
This work concerns the study of 6DSLAM algorithms with an application of robotic mobile mapping systems. The architecture of the 6DSLAM algorithm is designed for evaluation of different data registration strategies. The algorithm is composed of the i
Externí odkaz:
https://doaj.org/article/947056e550274a6ebe13f90cbc8eccce
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