Zobrazeno 1 - 10
of 1 944
pro vyhledávání: '"Arvanitidis A"'
Stability guarantees are crucial when ensuring that a fully autonomous robot does not take undesirable or potentially harmful actions. We recently proposed the Neural Contractive Dynamical Systems (NCDS), which is a neural network architecture that g
Externí odkaz:
http://arxiv.org/abs/2411.11405
The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to practitioners. Previously, counte
Externí odkaz:
http://arxiv.org/abs/2411.02259
Autor:
Christos Arvanitidis, Boris Barov, Alberto Basset, Klaas Deneudt, Montserrat González Ferreiro, Federico Drago, Cristina Huertas Olivares, Declan Kirrane, Dimitrios Koureas, Natalia Manola, Daniel Mietchen, Nicolas Pade, Lyubomir Penev, Gabriela Zuquim, Yannis Ioannidis
Publikováno v:
Research Ideas and Outcomes, Vol 10, Iss , Pp 1-5 (2024)
A network of European organisations is coordinating a workshop in New York (USA) on September 26, 2024, as part of the Science Summit 2024 at the 79th Session of the UN General Assembly (UNGA79). This network represents active communities from the fi
Externí odkaz:
https://doaj.org/article/1d1756de4eb149cfa7e38ba82fd7e44e
One of the main challenges in modern deep learning is to understand why such over-parameterized models perform so well when trained on finite data. A way to analyze this generalization concept is through the properties of the associated loss landscap
Externí odkaz:
http://arxiv.org/abs/2307.04719
Bayesian neural networks often approximate the weight-posterior with a Gaussian distribution. However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates. We propose a simple parametric approxima
Externí odkaz:
http://arxiv.org/abs/2306.07158
Autor:
Michail Arvanitidis, David Jiménez-Grande, Nadège Haouidji-Javaux, Deborah Falla, Eduardo Martinez-Valdes
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-16 (2024)
Abstract We aimed to assess high-density surface electromyography (HDsEMG)-torque relationships in the presence of delayed onset trunk muscle soreness (DOMS) and the effect of these relationships on torque steadiness (TS) and lumbar movement during c
Externí odkaz:
https://doaj.org/article/f67bfadc035346158a6bceb4fa604d73
Publikováno v:
BMJ Open, Vol 14, Iss 7 (2024)
Introduction Wearable neuromuscular and biomechanical biofeedback technology has the potential to improve patient outcomes by facilitating exercise interventions. We will conduct a systematic review to examine whether the addition of wearable biofeed
Externí odkaz:
https://doaj.org/article/a5cec214a7d84c728157088d828907a2
In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In practice, motion learning methods capture relevant patterns and adjust th
Externí odkaz:
http://arxiv.org/abs/2203.07761
Publikováno v:
In Computers and Chemical Engineering October 2024 189
Autor:
Christos Arvanitidis, Alberto Basset, Peter van Tienderen, Lucas de Moncuit, Cristina Huertas Olivares, Cristina Di Muri, Ana Mellado, Wouter Los
Publikováno v:
Biodiversity Data Journal, Vol 12, Iss , Pp 1-11 (2024)
Papers including articles that are produced because of the activities of LifeWatch ERIC, in the context of its second implementation period (2022 - 2026) and through the implementation of its new Strategic Working Plan, are published in this special
Externí odkaz:
https://doaj.org/article/20205580cc6c44b3832e6a31a8bdcd63