A5101971371- Educational and Social Studies
- Hannah Arendt's Political Philosophy
- Political Theology and Sovereignty
- Critical Theory and Philosophy
- Neural Networks and Applications
- Italian Fascism and Post-war Society
- Privacy-Preserving Technologies in Data
- Italian Social Issues and Migration
- Stochastic Gradient Optimization Techniques
- Data Mining Algorithms and Applications
- Psychoanalysis, Philosophy, and Politics
- Machine Learning and Algorithms
- Italian Literature and Culture
- Foucault, Power, and Ethics
- Rough Sets and Fuzzy Logic
- Political Philosophy and Ethics
- Data Management and Algorithms
- Historical and Environmental Studies
- Adversarial Robustness in Machine Learning
- Domain Adaptation and Few-Shot Learning
- Religious and Theological Studies
- Religion and Society Interactions
- Machine Learning and Data Classification
- Zoonotic diseases and public health
- Philosophical and Cultural Analysis
University of Perugia
2025
University of Turin
2010-2024
Italian Aerospace Research Centre
2024
Scuola Normale Superiore
2023
University of Naples Federico II
2004-2021
University of Edinburgh
2021
École Normale Supérieure
2019
Policlinico Universitario di Catania
2017
Istituto Superiore di Sanità
2017
Università Cattolica del Sacro Cuore
2016
One Health (OH) positions health professionals as agents for change and provides a platform to manage determinants of that are often not comprehensively captured in medicine or public alone. However, due the organisation societies disciplines, sectoral allocation resources, development transdisciplinary approaches requires effort perseverance. Therefore, there is need provide evidence on added value OH governments, researchers, funding bodies stakeholders. This paper outlines conceptual...
Coordination and governanceIn policy cycles, multiple rounds of agenda setting, formulation, decision-making, implementation evaluation lead to the creation, revision policies. 21We believe that, in terms interdisciplinary, intersectoral multi-institutional One Health approach, knowledge integration at every stage development, cycle, could strengthen coordination governance implementation.Although some from different disciplines, institutions sectors can, does, take place intuitively, many...
Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated (FL) has been emerging as a method for privacy-preserving pooling of datasets employing collaborative training institutions by iteratively globally aggregating locally trained models. One critical performance challenge FL is operating on not independently and identically distributed (non-IID) among the federation participants. Even though this fragility...
Developing predictive computational models of metabolism using mechanistic approaches is complex and resource intensive. Data-driven offer a reliable, fast, continuously updating solution for analytics. Previously, we developed the Personalized Metabolic Avatar (PMA), gated recurrent unit deep learning model, to forecast personalized weight variations based on macronutrient composition daily energy balance. This model allows diet plan simulations tailored goal setting, empowering individuals...
The last decade has witnessed a massive deployment of Machine Learning tools in everyday life automated tasks. Neural Networks are nowadays use growing number application areas because their excellent performances. Unfortunately, it been shown by many researchers that they can be attacked and fooled several different ways, this dangerously impair ability to correctly perform In paper we describe watermarking algorithm protect verify the integrity (Deep) when deployed safety critical systems,...
The essay identifies three ontological-political paradigms that are prominent in contemporary debate: the first, derived from Heidegger, is "destituent"; second, elaborated by Deleuze, "constituent"; and third, which refers above all to work of Claude Lefort, "instituting." While first two, forms they have assumed philosophy, give rise a politically ineffective outcome, third opens up new space thought for political praxis.
Federated Learning (FL) is becoming popular in different industrial sectors where data access critical for security, privacy and the economic value of itself. Unlike traditional machine learning, all must be globally gathered analysis, FL makes it possible to extract knowledge from distributed across organizations that can coupled with Machine paradigms. In this work, we replicate, using Learning, analysis a pooled dataset (with AdaBoost) has been used define PRAISE score, which today among...
Federated Learning has been proposed to develop better AI systems without compromising the privacy of final users and legitimate interests private companies. Initially deployed by Google predict text input on mobile devices, FL in many other industries. Since its introduction, mainly exploited inner working neural networks gradient descent-based algorithms either exchanging weights model or gradients computed during learning. While this approach very successful, it rules out applying...
In the following excerpt from Bios , Esposito sketches template of immunity as a response to what he calls "hermeneutic block" in Foucault's notion biopolitics. After singling out those moments greatest tension reading biopolitics especially it relates Nazi thanatopolitics, sets detail most important features immunization paradigm. Consisting three dispositifs namely sovereignty, property, and liberty, immunitary paradigm has for decisively modern inflection. Indeed cannot be thought apart...
Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated (FL) and Edge Inference are examples of DML. While tools for DML (especially FL) starting to flourish, many not flexible portable enough experiment with novel processors (e.g., RISC-V), non-fully connected network topologies, asynchronous collaboration schemes. We overcome these limitations via a domain-specific language allowing us map schemes an underlying middleware, i.e....
Abstract Linear least squares is one of the most widely used regression methods in many fields. The simplicity model allows this method to be when data scarce and practitioners gather some insight into problem by inspecting values learnt parameters. In paper we propose a variant linear allowing partition input features groups variables that they require contribute similarly final result. We show new formulation not convex provide two alternative deal with problem: non-exact based on an...