Zobrazeno 1 - 10
of 29 117
pro vyhledávání: '"Ioannou, A"'
Large neural networks achieve remarkable performance, but their size hinders deployment on resource-constrained devices. While various compression techniques exist, parameter sharing remains relatively unexplored. This paper introduces Fine-grained P
Externí odkaz:
http://arxiv.org/abs/2411.09816
In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity throughout the enti
Externí odkaz:
http://arxiv.org/abs/2411.03171
Autor:
Caro, Matthias C., Eisert, Jens, Hinsche, Marcel, Ioannou, Marios, Nietner, Alexander, Sweke, Ryan
We consider the problem of testing and learning from data in the presence of resource constraints, such as limited memory or weak data access, which place limitations on the efficiency and feasibility of testing or learning. In particular, we ask the
Externí odkaz:
http://arxiv.org/abs/2410.23969
Achieving stable bipedal walking on surfaces with unknown motion remains a challenging control problem due to the hybrid, time-varying, partially unknown dynamics of the robot and the difficulty of accurate state and surface motion estimation. Surfac
Externí odkaz:
http://arxiv.org/abs/2410.11799
Autor:
Puy, Andreu, Gimeno, Elisabet, Beltran, Francesc S., Dolado, Ruth, Miguel, M. Carmen, Ioannou, Christos C., Pastor-Satorras, Romualdo
Risk perception plays a key role in shaping the collective behavior of moving animal groups, yet the effects of variation in perceived risk within groups is unknown. Here, we merge two subgroups of fish with different levels of perceived risk, manipu
Externí odkaz:
http://arxiv.org/abs/2410.09264
Autor:
Mohammadshahi, Aida, Ioannou, Yani
Knowledge Distillation is a commonly used Deep Neural Network compression method, which often maintains overall generalization performance. However, we show that even for balanced image classification datasets, such as CIFAR-100, Tiny ImageNet and Im
Externí odkaz:
http://arxiv.org/abs/2410.08407
Autor:
Dehghani, Farzaneh, Dibaji, Mahsa, Anzum, Fahim, Dey, Lily, Basdemir, Alican, Bayat, Sayeh, Boucher, Jean-Christophe, Drew, Steve, Eaton, Sarah Elaine, Frayne, Richard, Ginde, Gouri, Harris, Ashley, Ioannou, Yani, Lebel, Catherine, Lysack, John, Arzuaga, Leslie Salgado, Stanley, Emma, Souza, Roberto, Santos, Ronnie de Souza, Wells, Lana, Williamson, Tyler, Wilms, Matthias, Wahid, Zaman, Ungrin, Mark, Gavrilova, Marina, Bento, Mariana
Artificial Intelligence (AI) has paved the way for revolutionary decision-making processes, which if harnessed appropriately, can contribute to advancements in various sectors, from healthcare to economics. However, its black box nature presents sign
Externí odkaz:
http://arxiv.org/abs/2408.15550
Autor:
Wilkens, Jadwiga, Ioannou, Marios, Derbyshire, Ellen, Eisert, Jens, Hangleiter, Dominik, Roth, Ingo, Haferkamp, Jonas
Analog quantum simulation allows for assessing static and dynamical properties of strongly correlated quantum systems to high precision. To perform simulations outside the reach of classical computers, accurate and reliable implementations of the ant
Externí odkaz:
http://arxiv.org/abs/2408.11105
The latest advancements in Distributed Ledger Technology (DLT), and payment architectures such as the UK's New Payments Architecture, present opportunities for leveraging the hidden informational value and intelligence within payments. In this paper,
Externí odkaz:
http://arxiv.org/abs/2406.17512
Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be biased towa
Externí odkaz:
http://arxiv.org/abs/2406.17073