Zobrazeno 1 - 10
of 2 804
pro vyhledávání: '"Pantazi A"'
Autor:
Mañosa, Víctor, Pantazi, Chara
In this work we investigate the set of cubic Hamiltonian vector fields for which their associated Kahan-Hirota-Kimura maps preserve the original Hamiltonian function. We analyze these fields in $\mathbb{R}^2$ and $\mathbb{R}^4$. We also study a famil
Externí odkaz:
http://arxiv.org/abs/2405.01321
Autor:
Ortner, Thomas, Petschenig, Horst, Vasilopoulos, Athanasios, Renner, Roland, Brglez, Špela, Limbacher, Thomas, Piñero, Enrique, Barranco, Alejandro Linares, Pantazi, Angeliki, Legenstein, Robert
There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios,
Externí odkaz:
http://arxiv.org/abs/2405.05141
We consider a three dimensional complex polynomial, or rational, vector field (equivalently, a two-form in three variables) which admits a Liouvillian first integral. We prove that there exists a first integral whose differential is the product of a
Externí odkaz:
http://arxiv.org/abs/2310.20451
Autor:
Farinha, Matilde Tristany, Ortner, Thomas, Dellaferrera, Giorgia, Grewe, Benjamin, Pantazi, Angeliki
Artificial Neural Networks (ANNs) trained with Backpropagation (BP) excel in different daily tasks but have a dangerous vulnerability: inputs with small targeted perturbations, also known as adversarial samples, can drastically disrupt their performa
Externí odkaz:
http://arxiv.org/abs/2309.17348
In this work we explain the relevance of the Differential Galois Theory in the semiclassical (or WKB) quantification of some two degree of freedom potentials. The key point is that the semiclassical path integral quantification around a particular so
Externí odkaz:
http://arxiv.org/abs/2307.09318
Autor:
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec, Giovanni Cherubini, Angeliki Pantazi, Wulfram Gerstner
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that th
Externí odkaz:
https://doaj.org/article/232a98336e0941d79563834bb5c1b24e
Autor:
Stanojevic, Ana, Woźniak, Stanisław, Bellec, Guillaume, Cherubini, Giovanni, Pantazi, Angeliki, Gerstner, Wulfram
Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks (SNNs) than artificial neural networks (ANNs). This is puzzling given th
Externí odkaz:
http://arxiv.org/abs/2306.08744
Autor:
Schnider, Yannick, Wozniak, Stanislaw, Gehrig, Mathias, Lecomte, Jules, von Arnim, Axel, Benini, Luca, Scaramuzza, Davide, Pantazi, Angeliki
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge or in rob
Externí odkaz:
http://arxiv.org/abs/2304.07139
Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks. However, BPTT introduces severe limitations, such as the requirement to propagate information backwar
Externí odkaz:
http://arxiv.org/abs/2304.05124
Autor:
von Arnim, Axel, Lecomte, Jules, Borras, Naima Elosegui, Wozniak, Stanislaw, Pantazi, Angeliki
Publikováno v:
Front. Neurorobot. 18:1290965
Optical identification is often done with spatial or temporal visual pattern recognition and localization. Temporal pattern recognition, depending on the technology, involves a trade-off between communication frequency, range and accurate tracking. W
Externí odkaz:
http://arxiv.org/abs/2303.07169