Výsledky vyhledávání - "Cedric Renggli"

Akademický článek

Decoding EEG Brain Activity for Multi-Modal Natural Language Processing

Autor: Nora Hollenstein, Cedric Renggli, Benjamin Glaus, Maria Barrett, Marius Troendle, Nicolas Langer, Ce Zhang

Publikováno v: Frontiers in Human Neuroscience, Vol 15 (2021)

Until recently, human behavioral data from reading has mainly been of interest to researchers to understand human cognition. However, these human language processing signals can also be beneficial in machine learning-based natural language processing

Externí odkaz: https://doaj.org/article/25e849a3d8824e51a3215e6ef7fb3ab7

Zobrazit plný text záznamu

Dynamic Human Evaluation for Relative Model Comparisons

Autor: Thórhildur Thorleiksdóttir, Cedric Renggli, Nora Hollenstein, Ce Zhang

Publikováno v: Thorleiksdóttir, T, Renggli, C, Hollenstein, N & Zhang, C 2022, Dynamic Human Evaluation for Relative Model Comparisons . in Proceedings of the Thirteenth Language Resources and Evaluation Conference . European Language Resources Association, Marseille, France, pp. 5946-5955 . < https://aclanthology.org/2022.lrec-1.639 >
Proceedings of the Thirteenth Language Resources and Evaluation Conference
University of Copenhagen

Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to correlate poo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be3ae94c02823d100ffde10cf34be889
https://curis.ku.dk/portal/da/publications/dynamic-human-evaluation-for-relative-model-comparisons(f26cf0d0-6301-41d7-a749-3e031f8a0726).html

Zobrazit plný text záznamu

In-Database Machine Learning with CorgiPile: Stochastic Gradient Descent without Full Data Shuffle

Autor: Lijie Xu, Shuang Qiu, Binhang Yuan, Jiawei Jiang, Cedric Renggli, Shaoduo Gan, Kaan Kara, Guoliang Li, Ji Liu, Wentao Wu, Jieping Ye, Ce Zhang

Publikováno v: SIGMOD '22: Proceedings of the 2022 International Conference on Management of Data

Stochastic gradient descent (SGD) is the cornerstone of modern ML systems. Despite its computational efficiency, SGD requires random data access that is inherently inefficient when implemented in systems that rely on block-addressable secondary stora

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66c43b124605382f450f36aa940f2a7f
https://hdl.handle.net/20.500.11850/557151

Zobrazit plný text záznamu

Observer Dependent Lossy Image Compression

Autor: Maurice Weber, Ce Zhang, Cedric Renggli, Helmut Grabner

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030712778
GCPR
Pattern Recognition

Deep neural networks have recently advanced the state-of-the-art in image compression and surpassed many traditional compression algorithms. The training of such networks involves carefully trading off entropy of the latent representation against rec

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c600d44bbb812e485ad4cb5fb11feed
https://doi.org/10.1007/978-3-030-71278-5_10

Zobrazit plný text záznamu

Ease.ml/ci and Ease.ml/meter in Action: Towards Data Management for Statistical Generalization

Autor: Wentao Wu, Kevin Schawinski, Frances Ann Hubis, Ce Zhang, Bojan Karlas, Cedric Renggli

Publikováno v: Proceedings of the VLDB Endowment, 12 (12)

Developing machine learning (ML) applications is similar to developing traditional software-it is often an iterative process in which developers navigate within a rich space of requirements, design decisions, implementations, empirical quality, and p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a639b417a94638526a87bb906e4ef419
https://hdl.handle.net/20.500.11850/395903

Zobrazit plný text záznamu

SparCML: High-Performance Sparse Communication for Machine Learning

Autor: Torsten Hoefler, Mehdi Aghagolzadeh, Dan Alistarh, Saleh Ashkboos, Cedric Renggli

Publikováno v: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
SC

Applying machine learning techniques to the quickly growing data in science and industry requires highly-scalable algorithms. Large datasets are most commonly processed "data parallel" distributed across many nodes. Each node's contribution to the ov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::626f561b7cb78facdc28d49f7928f543
http://arxiv.org/abs/1802.08021

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání