Zobrazeno 1 - 10
of 8 321
pro vyhledávání: '"Innocenti P."'
Autor:
Cremonesi, Francesco, Innocenti, Lucia, Ourselin, Sebastien, Goh, Vicky, Antonelli, Michela, Lorenzi, Marco
Background. Federated learning (FL) has gained wide popularity as a collaborative learning paradigm enabling collaborative AI in sensitive healthcare applications. Nevertheless, the practical implementation of FL presents technical and organizational
Externí odkaz:
http://arxiv.org/abs/2412.06494
Autor:
Innocenti, Francesco, Kinghorn, Paul, Yun-Farmbrough, Will, Varona, Miguel De Llanza, Singh, Ryan, Buckley, Christopher L.
We introduce JPC, a JAX library for training neural networks with Predictive Coding. JPC provides a simple, fast and flexible interface to train a variety of PC networks (PCNs) including discriminative, generative and hybrid models. Unlike existing l
Externí odkaz:
http://arxiv.org/abs/2412.03676
This study investigates the interactions between tides, storm surge, river flow, and power peaking in the microtidal Neretva River estuary, Croatia. Based on the existing NS_Tide tool, the study proposes a new non-stationary harmonic model adapted fo
Externí odkaz:
http://arxiv.org/abs/2411.13391
Despite modular conditions to guarantee stability for large-scale systems have been widely studied, few methods are available to tackle the case of networks with multiple equilibria. This paper introduces small-gain like sufficient conditions for 2-c
Externí odkaz:
http://arxiv.org/abs/2411.09550
Autor:
Rojas-Innocenti, Sebastián, Baeyens, Enrique, Martín-Crespo, Alejandro, Saludes-Rodil, Sergio, Frechoso, Fernando
The flexibility of industrial power consumption plays a key role in the transition to renewable energy systems, contributing to grid stability, cost reduction and decarbonization efforts. This paper presents a novel methodology to quantify and optimi
Externí odkaz:
http://arxiv.org/abs/2411.09279
Two-dimensional particle-in-cell (PIC) simulations explore the collisionless tearing instability developing in a Harris equilibrium configuration in a pair (electron-positron) plasma, with no guide field, for a range of parameters from non-relativist
Externí odkaz:
http://arxiv.org/abs/2410.05619
Quantum extreme learning machines (QELMs) leverage untrained quantum dynamics to efficiently process information encoded in input quantum states, avoiding the high computational cost of training more complicated nonlinear models. On the other hand, q
Externí odkaz:
http://arxiv.org/abs/2409.06782
Autor:
Taiello, Riccardo, Cansiz, Sergen, Vesin, Marc, Cremonesi, Francesco, Innocenti, Lucia, Önen, Melek, Lorenzi, Marco
Deploying federated learning (FL) in real-world scenarios, particularly in healthcare, poses challenges in communication and security. In particular, with respect to the federated aggregation procedure, researchers have been focusing on the study of
Externí odkaz:
http://arxiv.org/abs/2409.00974
In the last few years the literature has witnessed a remarkable surge of interest for chaotic maps implemented by discrete-time (DT) memristor circuits. This paper investigates on the reasons underlying this type of chaotic behavior. To this end, the
Externí odkaz:
http://arxiv.org/abs/2408.16352
Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before updating weights. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to its infer
Externí odkaz:
http://arxiv.org/abs/2408.11979