Zobrazeno 1 - 10
of 3 995
pro vyhledávání: '"Cina A"'
Autor:
Yingfu Xu, Kevin Shidqi, Gert-Jan van Schaik, Refik Bilgic, Alexandra Dobrita, Shenqi Wang, Roy Meijer, Prithvish Nembhani, Cina Arjmand, Pietro Martinello, Anteneh Gebregiorgis, Said Hamdioui, Paul Detterer, Stefano Traferro, Mario Konijnenburg, Kanishkan Vadivel, Manolis Sifalakis, Guangzhi Tang, Amirreza Yousefzadeh
Publikováno v:
Frontiers in Neuroscience, Vol 18 (2024)
Neuromorphic processors promise low-latency and energy-efficient processing by adopting novel brain-inspired design methodologies. Yet, current neuromorphic solutions still struggle to rival conventional deep learning accelerators' performance and ar
Externí odkaz:
https://doaj.org/article/b9216b9001bd425a90e3fae1a6231a5b
Autor:
Villani, Francesco, Lazzaro, Dario, Cinà, Antonio Emanuele, Dell'Amico, Matteo, Biggio, Battista, Roli, Fabio
Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase. These attacks typically require re-clustering the entire dataset mult
Externí odkaz:
http://arxiv.org/abs/2408.07558
Despite explainable AI (XAI) has recently become a hot topic and several different approaches have been developed, there is still a widespread belief that it lacks a convincing unifying foundation. On the other hand, over the past centuries, the very
Externí odkaz:
http://arxiv.org/abs/2407.18782
Autor:
Arjmand, Cina, Xu, Yingfu, Shidqi, Kevin, Dobrita, Alexandra F., Vadivel, Kanishkan, Detterer, Paul, Sifalakis, Manolis, Yousefzadeh, Amirreza, Tang, Guangzhi
Neuromorphic processors are well-suited for efficiently handling sparse events from event-based cameras. However, they face significant challenges in the growth of computing demand and hardware costs as the input resolution increases. This paper prop
Externí odkaz:
http://arxiv.org/abs/2406.17483
Autor:
Chen, Zhang, Demetrio, Luca, Gupta, Srishti, Feng, Xiaoyi, Xia, Zhaoqiang, Cinà, Antonio Emanuele, Pintor, Maura, Oneto, Luca, Demontis, Ambra, Biggio, Battista, Roli, Fabio
Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks' vulnerability t
Externí odkaz:
http://arxiv.org/abs/2406.10090
Matter-wave interferometry is essential to both science and technology. Phase-space squeezing has been shown to be an advantageous source of atoms, whereby the spread in momentum is decreased. Here, we show that the opposite squeezing may be just as
Externí odkaz:
http://arxiv.org/abs/2405.16972
Detecting out-of-distribution (OOD) instances is crucial for the reliable deployment of machine learning models in real-world scenarios. OOD inputs are commonly expected to cause a more uncertain prediction in the primary task; however, there are OOD
Externí odkaz:
http://arxiv.org/abs/2405.12658
Autor:
Cinà, Antonio Emanuele, Rony, Jérôme, Pintor, Maura, Demetrio, Luca, Demontis, Ambra, Biggio, Battista, Ayed, Ismail Ben, Roli, Fabio
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number of forward
Externí odkaz:
http://arxiv.org/abs/2404.19460
Autor:
van Geloven, Nan, Keogh, Ruth H, van Amsterdam, Wouter, Cinà, Giovanni, Krijthe, Jesse H., Peek, Niels, Luijken, Kim, Magliacane, Sara, Morzywołek, Paweł, van Ommen, Thijs, Putter, Hein, Sperrin, Matthew, Wang, Junfeng, Weir, Daniala L., Didelez, Vanessa
Prediction models are increasingly proposed for guiding treatment decisions, but most fail to address the special role of treatments, leading to inappropriate use. This paper highlights the limitations of using standard prediction models for treatmen
Externí odkaz:
http://arxiv.org/abs/2402.17366
Autor:
Cinà, Antonio Emanuele, Villani, Francesco, Pintor, Maura, Schönherr, Lea, Biggio, Battista, Pelillo, Marcello
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investigate sparse $\ell_1$- and $\ell_
Externí odkaz:
http://arxiv.org/abs/2402.01879