no code implementations • 2 May 2024 • Davide Frizzo, Francesco Borsatti, Alessio Arcudi, Antonio De Moliner, Roberto Oboe, Gian Antonio Susto
Anomaly detection (AD) is a crucial process often required in industrial settings.
1 code implementation • 29 Apr 2024 • Valentina Zaccaria, Chiara Masiero, David Dandolo, Gian Antonio Susto
While Machine Learning has become crucial for Industry 4. 0, its opaque nature hinders trust and impedes the transformation of valuable insights into actionable decision, a challenge exacerbated in the evolving Industry 5. 0 with its human-centric focus.
no code implementations • 10 Apr 2024 • Marina Ceccon, Davide Dalle Pezze, Alessandro Fabris, Gian Antonio Susto
This method aims to mitigate forgetting while adapting to new classes and domain shifts by combining the advantages of the Replay and Pseudo-Label methods and solving their limitations in the proposed scenario.
no code implementations • 23 Mar 2024 • Luca Vittorio Piron, Matteo Cederle, Marina Ceccon, Federico Chiariotti, Alessandro Fabris, Marco Fabris, Gian Antonio Susto
As Machine Learning systems become increasingly popular across diverse application domains, including those with direct human implications, the imperative of equity and algorithmic fairness has risen to prominence in the Artificial Intelligence community.
no code implementations • 19 Mar 2024 • Nikola Bugarin, Jovana Bugaric, Manuel Barusco, Davide Dalle Pezze, Gian Antonio Susto
Anomaly Detection is a relevant problem in numerous real-world applications, especially when dealing with images.
no code implementations • 2 Mar 2024 • Valentina Zaccaria, David Dandolo, Chiara Masiero, Gian Antonio Susto
Pursuing fast and robust interpretability in Anomaly Detection is crucial, especially due to its significance in practical applications.
no code implementations • 14 Feb 2024 • Alberto Sinigaglia, Niccolò Turcato, Alberto Dalla Libera, Ruggero Carli, Gian Antonio Susto
This paper introduces innovative methods in Reinforcement Learning (RL), focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning.
1 code implementation • 2 Feb 2024 • Luca Della Libera, Jacopo Andreoli, Davide Dalle Pezze, Mirco Ravanelli, Gian Antonio Susto
In particular, we show through experimental studies on simulated run-to-failure turbofan engine degradation data that Bayesian deep learning models trained via Stein variational gradient descent consistently outperform with respect to convergence speed and predictive performance both the same models trained via parametric variational inference and their frequentist counterparts trained via backpropagation.
1 code implementation • 9 Oct 2023 • Alessio Arcudi, Davide Frizzo, Chiara Masiero, Gian Antonio Susto
The analysis demonstrates the effectiveness of ExIFFI in providing explanations for AD predictions.
no code implementations • 3 Jan 2023 • Natalie Gentner, Gian Antonio Susto
Motivated by the need to transfer and standardize established processes to different, non-identical environments and by the challenge of adapting to heterogeneous data representations, this work introduces the Domain Adaptation Neural Network with Cyclic Supervision (DBACS) approach.
no code implementations • 30 Dec 2022 • Tommaso Barbariol, Davide Masiero, Enrico Feltresi, Gian Antonio Susto
An Anomaly Detection (AD) System for Self-diagnosis has been developed for Multiphase Flow Meter (MPFM).
1 code implementation • 21 Dec 2022 • Davide Dalle Pezze, Eugenia Anello, Chiara Masiero, Gian Antonio Susto
The proposed technique scales and compresses the original images using a Super Resolution model which, to the best of our knowledge, is studied for the first time in the Continual Learning setting.
no code implementations • 4 Dec 2022 • Lucas Costa Brito, Gian Antonio Susto, Jorge Nei Brito, Marcus Antonio Viana Duarte
The monitoring of rotating machinery has now become a fundamental activity in the industry, given the high criticality in production processes.
no code implementations • 6 Oct 2022 • Lucas Costa Brito, Gian Antonio Susto, Jorge Nei Brito, Marcus Antonio Viana Duarte
Artificial Intelligence (AI) is one of the approaches that has been proposed to analyze the collected data (e. g., vibration signals) providing a diagnosis of the asset's operating condition.
no code implementations • 8 Aug 2022 • Davide Dalle Pezze, Denis Deronjic, Chiara Masiero, Diego Tosato, Alessandro Beghi, Gian Antonio Susto
For the first time, we study multi-label classification in the Domain Incremental Learning scenario.
no code implementations • 8 Jul 2022 • Elisa Marcelli, Tommaso Barbariol, Gian Antonio Susto
The detection of anomalous behaviours is an emerging need in many applications, particularly in contexts where security and reliability are critical aspects.
no code implementations • 17 Mar 2022 • Mattia Carletti, Matteo Terzi, Gian Antonio Susto
Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures.
1 code implementation • 13 Feb 2022 • Alberto Purpura, Gianmaria Silvello, Gian Antonio Susto
Learning to Rank (LETOR) algorithms are usually trained on annotated corpora where a single relevance label is assigned to each available document-topic pair.
no code implementations • 23 Dec 2021 • David Dandolo, Chiara Masiero, Mattia Carletti, Davide Dalle Pezze, Gian Antonio Susto
In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait.
no code implementations • 21 Dec 2021 • Matteo Terzi, Mattia Carletti, Gian Antonio Susto
By leveraging the IGE representation, we build a new defense method, Filtering As a Defense, that does not allow the attacker to entangle pixels to create malicious patterns.
1 code implementation • 30 Nov 2021 • Tommaso Barbariol, Gian Antonio Susto
Unsupervised anomaly detection tackles the problem of finding anomalies inside datasets without the labels availability; since data tagging is typically hard or expensive to obtain, such approaches have seen huge applicability in recent years.
1 code implementation • 3 Mar 2021 • Federico Zocco, Marco Maggipinto, Gian Antonio Susto, Seán McLoone
In this paper a "lazy" implementation of the FSCA algorithm (L-FSCA) is proposed, which, although not equivalent to FSCA due to the absence of submodularity, has the potential to yield comparable performance while being up to an order of magnitude faster to compute.
no code implementations • 23 Feb 2021 • Lucas Costa Brito, Gian Antonio Susto, Jorge Nei Brito, Marcus Antonio Viana Duarte
Therefore, a new approach for fault detection and diagnosis in rotating machinery is here proposed.
no code implementations • 22 Feb 2021 • Alberto Purpura, Karolina Buchner, Gianmaria Silvello, Gian Antonio Susto
LEarning TO Rank (LETOR) is a research area in the field of Information Retrieval (IR) where machine learning models are employed to rank a set of items.
no code implementations • 20 Aug 2020 • Marco Maggipinto, Matteo Terzi, Gian Antonio Susto
Deep Neural networks have gained lots of attention in recent years thanks to the breakthroughs obtained in the field of Computer Vision.
no code implementations • 3 Aug 2020 • Marco Maggipinto, Matteo Terzi, Gian Antonio Susto
Learning useful representations of complex data has been the subject of extensive research for many years.
no code implementations • 3 Aug 2020 • Marco Maggipinto, Gian Antonio Susto, Pratik Chaudhari
This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms.
no code implementations • 22 Jul 2020 • Matteo Terzi, Alessandro Achille, Marco Maggipinto, Gian Antonio Susto
Recent results show that features of adversarially trained networks for classification, in addition to being robust, enable desirable properties such as invertibility.
1 code implementation • 21 Jul 2020 • Mattia Carletti, Matteo Terzi, Gian Antonio Susto
Anomaly Detection is an unsupervised learning task aimed at detecting anomalous behaviours with respect to historical data.
no code implementations • 8 Oct 2019 • Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari
Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points.