Zobrazeno 1 - 10
of 22 141
pro vyhledávání: '"A Roeder"'
Decentralised learning enables the training of deep learning algorithms without centralising data sets, resulting in benefits such as improved data privacy, operational efficiency and the fostering of data ownership policies. However, significant dat
Externí odkaz:
http://arxiv.org/abs/2412.16079
Autor:
de Payrebrune, Kristin M., Flaßkamp, Kathrin, Ströhla, Tom, Sattel, Thomas, Bestle, Dieter, Röder, Benedict, Eberhard, Peter, Peitz, Sebastian, Stoffel, Marcus, Rutwik, Gulakala, Aditya, Borse, Wohlleben, Meike, Sextro, Walter, Raff, Maximilian, Remy, C. David, Yadav, Manish, Stender, Merten, van Delden, Jan, Lüddecke, Timo, Langer, Sabine C., Schultz, Julius, Blech, Christopher
Artificial intelligence (AI) is driving transformative changes across numerous fields, revolutionizing conventional processes and creating new opportunities for innovation. The development of mechatronic systems is undergoing a similar transformation
Externí odkaz:
http://arxiv.org/abs/2412.12230
Autor:
Ricci, L., Boccardi, B., Roeder, J., Perucho, M., Mattia, G., Kadler, M., Benke, P., Bartolini, V., Krichbaum, T. P., Madika, E.
The dynamic of relativistic jets in the inner parsec regions is deeply affected by the nature of the magnetic fields. The level of magnetization of the plasma, as well as the geometry of these fields on compact scales, have not yet been fully constra
Externí odkaz:
http://arxiv.org/abs/2411.19126
Autor:
Song, Kaidong, Zhou, Jingyuan, Wei, Chen, Ponnuchamy, Ashok, Bappy, Md Omarsany, Liao, Yuxuan, Jiang, Qiang, Du, Yipu, Evans, Connor J., Wyatt, Brian C., O'Sullivan, Thomas, Roeder, Ryan K., Anasori, Babak, Hoffman, Anthony J., Jin, Lihua, Duan, Xiangfeng, Zhang, Yanliang
Stretchable electronics capable of conforming to nonplanar and dynamic human body surfaces are central for creating implantable and on-skin devices for high-fidelity monitoring of diverse physiological signals. While various strategies have been deve
Externí odkaz:
http://arxiv.org/abs/2411.03339
Autor:
Ebel, Henrik, van Delden, Jan, Lüddecke, Timo, Borse, Aditya, Gulakala, Rutwik, Stoffel, Marcus, Yadav, Manish, Stender, Merten, Schindler, Leon, de Payrebrune, Kristin Miriam, Raff, Maximilian, Remy, C. David, Röder, Benedict, Raj, Rohit, Rentschler, Tobias, Tismer, Alexander, Riedelbauch, Stefan, Eberhard, Peter
Data-based methods have gained increasing importance in engineering, especially but not only driven by successes with deep artificial neural networks. Success stories are prevalent, e.g., in areas such as data-driven modeling, control and automation,
Externí odkaz:
http://arxiv.org/abs/2410.18358
Data integration methods aim to extract low-dimensional embeddings from high-dimensional outcomes to remove unwanted variations, such as batch effects and unmeasured covariates, across heterogeneous datasets. However, multiple hypothesis testing afte
Externí odkaz:
http://arxiv.org/abs/2410.04996
Autor:
Röder, Manuel, Schleif, Frank-Michael
This extended abstract explores the integration of federated learning with deep transfer hashing for distributed prediction tasks, emphasizing resource-efficient client training from evolving data streams. Federated learning allows multiple clients t
Externí odkaz:
http://arxiv.org/abs/2409.12575
Autor:
Srivastava, Nikit, Kuchelev, Denis, Ngoli, Tatiana Moteu, Shetty, Kshitij, Röder, Michael, Zahera, Hamada, Moussallem, Diego, Ngomo, Axel-Cyrille Ngonga
This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of harnessing li
Externí odkaz:
http://arxiv.org/abs/2409.11272
Publikováno v:
The Semantic Web . ISWC 2022. ISWC 2022. Lecture Notes in Computer Science, vol 13489. Springer, Cham
We consider fact-checking approaches that aim to predict the veracity of assertions in knowledge graphs. Five main categories of fact-checking approaches for knowledge graphs have been proposed in the recent literature, of which each is subject to pa
Externí odkaz:
http://arxiv.org/abs/2409.06692
Autor:
Röder, Manuel, Schleif, Frank-Michael
We present a numerically robust, computationally efficient approach for non-I.I.D. data stream sampling in federated client systems, where resources are limited and labeled data for local model adaptation is sparse and expensive. The proposed method
Externí odkaz:
http://arxiv.org/abs/2408.17108