Andrea Perin

JuliaUQ/UncertaintyQuantification.jl: v0.14.0

Jasper Behrensdorf, Ander Gray, Andrea Perin, Jan Grashorn et autres

UncertaintyQuantification v0.14.0 Diff since v0.13.0 This version fixes a serious bug in TransitionalMarkovChainMonteCarlo and introduces optional binning to the kernel density estimation among other things. There are no breaking changes. Merged pull requests: Add optional binning for EmpiricalDistribution (#269) (@FriesischScott) Test on …

de, fr (code pays fourni par la source)

¿Los motivos abyectos-discriminatorios incrementan la culpabilidad?: Introduccion a una propuesta conforme a la exigencia de ofensividad

Andrea Perin

Inteligencia artificial en el ámbito sanitario

Guillermo Lazcoz Moratinos, Andrea Perin

Leccion 20: inteligencia artificial en el ambito sanitario

Andrea Perin

Il reato discriminatorio quale “illecito online”: coordinate di diritto interno, comparato ed eurounitario

Andrea Perin

Giustizia penale e Unione Europea - Sguardo d'insieme (settembre - novembre 2024)

F Cassibba, Andrea Perin

Rassegna della giurisprudenza della Corte di Giustizia UE in materia penale

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory

Andrea Perin, Stéphane Deny

Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds considerable promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks -- with standard architectures trained in a standard, …

EnhancedBayesianNetworks.jl: A New Julia Framework for Multi Scenario Risk Assessment

Andrea Perin, Matteo Broggi, Michael Beer

Risk assessment is essential for identifying vulnerabilities, preventing disruptions, and enhancing decision-making processes. Traditional reliability evaluation techniques, such as Fault-Tree analysis, have been extensively used but have limitations in handling continuous random variables and uncertainties. Bayesian Networks, with their ability to integrate …

de (code pays fourni par la source)

How to Be Certain: Using Known Relations and Trust Discount to Determine Confidence About the Degree of Uncertainty

Niklas R. Winnewisser, Thomas Potthast, Felix Mett, Andrea Perin et autres

Ensuring certainty in the rapidly evolving digital twin environments amidst inherent uncertainty is paramount in decision-making for critical engineering systems. This paper presents a novel approach for quantifying and tracking confidence levels within a network of sensors and structural models, specifically addressing …

de, cn, gb (code pays fourni par la source)

A comparison between humans and AI at recognizing objects in unusual poses

Netta Ollikka, Amro Abbas, Andrea Perin, Markku Kilpeläinen et autres

Deep learning is closing the gap with human vision on several object recognition benchmarks. Here we investigate this gap for challenging images where objects are seen in unusual poses. We find that humans excel at recognizing objects in such poses. In contrast, …

fi, Afrique du Sud (code pays fourni par la source)

A comparison between humans and AI at recognizing objects in unusual poses

Netta Ollikka, Amro Abbas, Andrea Perin, Markku Kilpeläinen et autres

Deep learning is closing the gap with human vision on several object recognition benchmarks. Here we investigate this gap for challenging images where objects are seen in unusual poses. We find that humans excel at recognizing objects in such poses. In contrast, …

How to Be Certain: Using Known Relations and Trust Discount to Determine Confidence About the Degree of Uncertainty

Niklas R. Winnewisser, Thomas Potthast, Felix Mett, Andrea Perin et autres

Ensuring certainty in the rapidly evolving digital twin environments amidst inherent uncertainty is paramount in decision-making for critical engineering systems. This paper presents a novel approach for quantifying and tracking confidence levels within a network of sensors and structural models, specifically addressing …