Zobrazeno 1 - 10
of 1 162
pro vyhledávání: '"A. Adamos"'
Autor:
Pandurov, Milan, Humbel, Lukas, Sepp, Dmitry, Ttofari, Adamos, Thomm, Leon, Quoc, Do Le, Chandrasekaran, Siddharth, Santhanam, Sharan, Ye, Chuan, Bergman, Shai, Wang, Wei, Lundgren, Sven, Sagonas, Konstantinos, Ros, Alberto
Memory has become the primary cost driver in cloud data centers. Yet, a significant portion of memory allocated to VMs in public clouds remains unused. To optimize this resource, "cold" memory can be reclaimed from VMs and stored on slower storage or
Externí odkaz:
http://arxiv.org/abs/2409.13327
Autor:
Ijishakin, Ayodeji, Hadjasavilou, Adamos, Abdulaal, Ahmed, Montana-Brown, Nina, Townend, Florence, Spinelli, Edoardo, Fillipi, Massimo, Agosta, Federica, Cole, James, Malaspina, Andrea
Predicting survival in Amyotrophic Lateral Sclerosis (ALS) is a challenging task. Magnetic resonance imaging (MRI) data provide in vivo insight into brain health, but the low prevalence of the condition and resultant data scarcity limit training set
Externí odkaz:
http://arxiv.org/abs/2407.14191
Publikováno v:
ICML (2023), 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)
In visual object classification, humans often justify their choices by comparing objects to prototypical examples within that class. We may therefore increase the interpretability of deep learning models by imbuing them with a similar style of reason
Externí odkaz:
http://arxiv.org/abs/2306.03022
Autor:
José Fontoura-Matias, Davit George Chakhunashvili, Sian Copley, Łukasz Dembiński, Agnieszka Drosdzol-Cop, Adamos Hadjipanayis, Laura Reali, Artur Mazur
Publikováno v:
Frontiers in Pediatrics, Vol 12 (2024)
IntroductionTeenage parenthood presents multifaceted implications, affecting adolescent parents, their children, and extended families. Despite a decrease in teenage pregnancy rates across Europe, the phenomenon continues to present significant chall
Externí odkaz:
https://doaj.org/article/7b7225aeadfe4c9eb102260c863f83ca
Publikováno v:
In Engineering Fracture Mechanics 1 October 2024 309
Autor:
Wei, Xiaoxi, Faisal, A. Aldo, Grosse-Wentrup, Moritz, Gramfort, Alexandre, Chevallier, Sylvain, Jayaram, Vinay, Jeunet, Camille, Bakas, Stylianos, Ludwig, Siegfried, Barmpas, Konstantinos, Bahri, Mehdi, Panagakis, Yannis, Laskaris, Nikolaos, Adamos, Dimitrios A., Zafeiriou, Stefanos, Duong, William C., Gordon, Stephen M., Lawhern, Vernon J., Śliwowski, Maciej, Rouanne, Vincent, Tempczyk, Piotr
Transfer learning and meta-learning offer some of the most promising avenues to unlock the scalability of healthcare and consumer technologies driven by biosignal data. This is because current methods cannot generalise well across human subjects' dat
Externí odkaz:
http://arxiv.org/abs/2202.12950
Autor:
Bakas, Stylianos, Ludwig, Siegfried, Barmpas, Konstantinos, Bahri, Mehdi, Panagakis, Yannis, Laskaris, Nikolaos, Adamos, Dimitrios A., Zafeiriou, Stefanos
Building subject-independent deep learning models for EEG decoding faces the challenge of strong covariate-shift across different datasets, subjects and recording sessions. Our approach to address this difficulty is to explicitly align feature distri
Externí odkaz:
http://arxiv.org/abs/2202.03267
Publikováno v:
NeurIPS 2021
We study the theoretical convergence properties of random-search methods when optimizing non-convex objective functions without having access to derivatives. We prove that standard random-search methods that do not rely on second-order information co
Externí odkaz:
http://arxiv.org/abs/2110.13265
Autor:
Ludwig, Siegfried, Bakas, Stylianos, Adamos, Dimitrios A., Laskaris, Nikolaos, Panagakis, Yannis, Zafeiriou, Stefanos
Patterns of brain activity are associated with different brain processes and can be used to identify different brain states and make behavioral predictions. However, the relevant features are not readily apparent and accessible. To mine informative l
Externí odkaz:
http://arxiv.org/abs/2110.10009
In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns
Externí odkaz:
http://arxiv.org/abs/2110.08323