Epistemic AI

Informazioni relative al progetto

E-pi

ID dell’accordo di sovvenzione: 964505

DOI

10.3030/964505

Data della firma CE 17 Dicembre 2020

Data di avvio 1 Marzo 2021

Data di completamento 28 Febbraio 2026

Finanziato da

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Costo totale

€ 3 016 618,75

Contributo UE

€ 3 016 618,75

Coordinato da

OXFORD BROOKES UNIVERSITY
United Kingdom

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (6)

Report on epistemic reinforcement learning, with codebase
Report on pointwise optimisation under epistemic uncertainty
Report on methods from uncertainty theory
Report on epistemic learning theory
Report on use case definition
Report on set-based learning

Websites, patent fillings, videos etc. (2)

Thematic workshop no 1
Website and project logo

Project website and logo are finalised

Other (1)

Report on epistemic unsupervised learning, with code

Pubblicazioni

Peer reviewed articles (7)

DeepSmoke: Deep learning model for smoke detection and segmentation in outdoor environments

Autori: Salman Khan; Salman Khan; Khan Muhammad; Tanveer Hussain; Javier Del Ser; Fabio Cuzzolin; Siddhartha Bhattacharyya; Zahid Akhtar; Victor Hugo C. de Albuquerque
Pubblicato in: Expert Systems with Applications, 2021, Pagina/e 115-125, ISSN 0957-4174
Editore: Pergamon Press Ltd.
DOI: 10.1016/j.eswa.2021.115125

ROAD-R: the autonomous driving dataset with logical requirements

Autori: Eleonora Giunchiglia, Mihaela Cătălina Stoian, Salman Khan, Fabio Cuzzolin, Thomas Lukasiewicz
Pubblicato in: Machine Learning, Numero 112, 2023, Pagina/e 3261-3291, ISSN 0885-6125
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10994-023-06322-z

Fleet planning under demand and fuel price uncertainty using actor–critic reinforcement learning

Autori: Izaak L. Geursen, Bruno F. Santos, Neil Yorke-Smith
Pubblicato in: Journal of Air Transport Management, Numero 109, 2023, Pagina/e 102397, ISSN 0969-6997
Editore: Pergamon Press Ltd.
DOI: 10.1016/j.jairtraman.2023.102397

Uncertainty measures: A critical survey

Autori: Fabio Cuzzolin
Pubblicato in: Information Fusion, Numero 114, 2024, Pagina/e 102609, ISSN 1566-2535
Editore: Elsevier BV
DOI: 10.1016/j.inffus.2024.102609

Berth planning and real-time disruption recovery: a simulation study for a tidal port

Autori: Jaap-Jan van der Steeg, Menno Oudshoorn, Neil Yorke-Smith
Pubblicato in: Flexible Services and Manufacturing Journal, Numero 35, 2023, Pagina/e 70-110, ISSN 1936-6582
Editore: Springer Pub. Co.,
DOI: 10.1007/s10696-022-09473-8

Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review

Autori: Christelle Langley, Bogdan-Ionut Cirstea, Fabio Cuzzolin and Barbara J. Sahakian
Pubblicato in: Frontiers in Artificial Intelligence, Numero April 5 2022, 2022, ISSN 2624-8212
Editore: Frontiers Media S.A.
DOI: 10.3389/frai.2022.778852

ROAD: The ROad event Awareness Dataset for autonomous Driving

Autori: Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Suman Saha, Kossar Jeddisaravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Salman Khan, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, Fabio Cuzzolin
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, ISSN 1939-3539
Editore: IEEE
DOI: 10.1109/tpami.2022.3150906

Other (14)

Generalising realisability in statistical learning theory under epistemic uncertainty

Autori: F. Cuzzolin
Pubblicato in: arXiv preprint arXiv:2402.14759, Numero 22 Feb 2024, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2402.14759

An introduction to optimization under uncertainty -- A short survey

Autori: Shariatmadar, Keivan; Wang, Kaizheng; Hubbard, Calvin R.; Hallez, Hans; Moens, David
Pubblicato in: arXiv report arxiv.2212.00862, Numero 1 Dec 2022, 2022
Editore: Cornell University
DOI: 10.48550/arxiv.2212.00862

Credal learning theory

Autori: M. Caprio, M. Sultana, E. Elia and F. Cuzzolin
Pubblicato in: arXiv preprint arXiv:2402.00957, Numero 2 May 2024, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2402.00957

Reasoning with random sets: An agenda for the future

Autori: F. Cuzzolin
Pubblicato in: arXiv preprint arXiv:2401.09435, Numero 19 Dec 2023, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2401.09435

The intersection probability: betting with probability intervals

Autori: Fabio Cuzzolin
Pubblicato in: arXiv preprint arxiv.2201.01729, Numero 5 January 2022, 2022
Editore: Cornell University
DOI: 10.48550/arxiv.2201.01729

Uncertainty measures: The big picture

Autori: Fabio Cuzzolin
Pubblicato in: arXiv preprint arxiv.2104.06839, Numero 14 April 2021, 2021
Editore: Cornell University
DOI: 10.48550/arxiv.2104.06839

CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks

Autori: Kaizheng Wang, Keivan Shariatmadar, Shireen Kudukkil Manchingal, Fabio Cuzzolin, David Moens, Hans Hallez
Pubblicato in: arXiv preprint arXiv:2401.05043, Numero 2 Feb 2024, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2401.05043

Credal Wrapper of Model Averaging for Uncertainty Estimation on Out-Of-Distribution Detection

Autori: K. Wang, F. Cuzzolin, K. Shariatmadar, D. Moens, H. Hallez
Pubblicato in: arXiv preprint arXiv:2405.15047, Numero 23 May 2024, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2405.15047

Path Planning Problem under non-probabilistic Uncertainty

Autori: K. Shariatmadar
Pubblicato in: arXiv preprint arXiv.2212.01388, Numero 1 Dec 2022, 2022
Editore: Cornell University
DOI: 10.48550/arxiv.2212.01388

Random-Set Convolutional Neural Network (RS-CNN) for Epistemic Deep Learning

Autori: Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Keivan Shariatmadar, Fabio Cuzzolin
Pubblicato in: arXiv preprint arXiv:2307.05772, Numero 11 Jul 2023, 2023
Editore: Cornell University
DOI: 10.48550/arxiv.2307.05772

E-MCTS: Deep Exploration in Model-Based Reinforcement Learning by Planning with Epistemic Uncertainty

Autori: Oren, Yaniv; Spaan, Matthijs T. J.; Böhmer, Wendelin
Pubblicato in: arXiv preprint arxiv.2210.13455, Numero 30 Aug 2023, 2023
Editore: Cornell University
DOI: 10.48550/arxiv.2210.13455

Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing

Autori: Izzeddin Teeti, Valentina Musat, Salman Khan, Alexander Rast, Fabio Cuzzolin, Andrew Bradley
Pubblicato in: arXiv preprint arxiv.2201.03246, Numero 11 January 2022, 2022
Editore: Cornell University
DOI: 10.48550/arxiv.2201.03246

Generalisation of Total Uncertainty in AI: A Theoretical Study

Autori: K. Shariatmadar
Pubblicato in: arXiv preprint arXiv.2408.00946, Numero 1 Aug 2024, 2024
Editore: Cornell University
DOI: 10.48550/arxiv.2408.00946

A geometric approach to conditioning belief functions

Autori: Fabio Cuzzolin
Pubblicato in: arXiv preprint arxiv.2104.10651, Numero 21 April 2021, 2021
Editore: Cornell University
DOI: 10.48550/arxiv.2104.10651

Conference proceedings (18)

On the Estimation of Image-Matching Uncertainty in Visual Place Recognition

Autori: Mubariz Zaffar, Liangliang Nan, Julian F. P. Kooij
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Numero 31, 2024, Pagina/e 17743-17753
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.01680

Bayesian Deep Q-Learning via Sequential Monte Carlo

Autori: Pascal Van der Vaart, Matthijs T. J. Spaan, Neil Yorke-Smith
Pubblicato in: 16th European Workshop on Reinforcement Learning (EWRL 2023), Numero 14 Sep 2023, 2023
Editore: EWRL
DOI: 10.5281/zenodo.14245136

Bayesian Model-Free Deep Reinforcement Learning

Autori: Pascal van der Vaart
Pubblicato in: AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, Numero 6 May 2024, 2024, Pagina/e 2782-2784
Editore: IFAAMAS
DOI: 10.5555/3635637.3663285

A Hybrid Graph Network for Complex Activity Detection in Video

Autori: Salman Khan, Izzeddin Teeti, Andrew Bradley, Mohamed Elhoseiny, Fabio Cuzzolin
Pubblicato in: 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Numero 32, 2024, Pagina/e 6748-6758
Editore: IEEE
DOI: 10.1109/wacv57701.2024.00662

Diverse Projection Ensembles for Distributional Reinforcement Learning

Autori: Zanger, Moritz A.; Böhmer, Wendelin; Spaan, Matthijs T. J.
Pubblicato in: 16th European Workshop on Reinforcement Learning (EWRL 2023), Numero 14 Sep 2023, 2023
Editore: EWRL
DOI: 10.48550/arxiv.2306.07124

Bayesian Ensembles for Exploration in Deep Q-Learning

Autori: Pascal Van der Vaart, Neil Yorke-Smith, Matthijs T. J. Spaan
Pubblicato in: Sixteenth Workshop on Adaptive and Learning Agents (ALA 2024), Numero 6 May 2024, 2024, Pagina/e 2528 - 2530
Editore: Adaptive Learning Agents Workshop 2024
DOI: 10.5555/3635637.3663216

Interval Reduced Order Surrogate Modelling Framework for Uncertainty Quantification

Autori: Ghifari A. Faza, Keivan Shariatmadar, Hans Hallez, David Moens
Pubblicato in: AIAA SCITECH 2024 Forum, Numero 4 Jan 2024, 2024
Editore: American Institute of Aeronautics and Astronautics
DOI: 10.2514/6.2024-0387

A generalisation of the Bellman Equation in Epistemic Reinforcement Learning

Autori: K. Shariatmadar, J. Golub, A. Faza, D. Moens
Pubblicato in: XAI workshop, Numero May 23 2024, 2024
Editore: Eindhoven Artificial Intelligence Systems Institute
DOI: 10.5281/zenodo.14217032

Epistemic Deep Learning

Autori: Shireen Kudukkil Manchingal, Fabio Cuzzolin
Pubblicato in: ICML 2022 Workshop on Distribution-Free Uncertainty Quantification, Numero 23 Jul 2022, 2022
Editore: ICML
DOI: 10.48550/arxiv.2206.07609

Diverse Projection Ensembles for Distributional Reinforcement Learning

Autori: Moritz Akiya Zanger, Wendelin Boehmer, Matthijs T. J. Spaan
Pubblicato in: The Twelfth International Conference on Learning Representations (ICLR 2024), Numero 7 May 2024, 2024
Editore: ICLR
DOI: 10.5281/zenodo.14236990

Credal Deep Ensembles for Uncertainty Quantification

Autori: K. Wang, K. Shariatmadar, S. Manchingal, F. Cuzzolin, D. Moens and H. Hallez
Pubblicato in: Thirty-eighth Annual Conference on Neural Information Processing Systems, Numero Dec 9 2024, 2024
Editore: NeurIPS Foundation
DOI: 10.5281/zenodo.14217205

Optimization Under Epistemic Uncertainty With a Focus on Decision-Focused Learning

Autori: Noah Schutte
Pubblicato in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, Numero 3-9 Aug 2024, 2024, Pagina/e 8504-8505
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/967

Science of AI - Total Uncertainty in AI

Autori: Keivan Shariatmadar
Pubblicato in: Leuven.AI Workshop, Numero Jun 3 2024, 2024
Editore: KU Leuven
DOI: 10.5281/zenodo.14223938

Robust Losses for Decision-Focused Learning

Autori: Noah Schutte, Krzysztof Postek, Neil Yorke-Smith
Pubblicato in: Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, Numero 3-9 Aug 2024, 2024, Pagina/e 4868-4875
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2024/538

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

Autori: Aduen Benjumea, Izzeddin Teeti, Fabio Cuzzolin, Andrew Bradley
Pubblicato in: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Numero 23 December 2021, 2021
Editore: IEEE
DOI: 10.48550/arxiv.2112.11798

Credal learning theory

Autori: Michele Caprio, Maryam Sultana, Eleni Elia and Fabio Cuzzolin
Pubblicato in: Thirty-eighth Annual Conference on Neural Information Processing Systems, Numero Dec 9 2024, 2024
Editore: NeurIPS Foundation
DOI: 10.5281/zenodo.14216819

Multi-weather city: Adverse weather stacking for autonomous driving

Autori: Valentina Mușat, Ivan Fursa, Paul Newman, Fabio Cuzzolin, Andrew Bradley
Pubblicato in: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Numero 11-17 Oct 2021, 2022
Editore: IEEE
DOI: 10.1109/iccvw54120.2021.00325

ROAD-R: The Autonomous Driving Dataset with Logical Requirements

Autori: E. Giunchiglia, M. Stoian, S. Khan, F. Cuzzolin and T. Lukasiewicz
Pubblicato in: IJCAI 2022 - Workshop on Artificial Intelligence for Autonomous Driving (AI4AD 2022), Numero 23 Jul 2022, 2022
Editore: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.48550/arxiv.2210.01597

Monographic books (1)

Epistemic Uncertainty in Artificial Intelligence

Autori: Fabio Cuzzolin, Maryam Sultana
Pubblicato in: Lecture Notes in Computer Science, Numero 23 Apr 2024, 2024, ISBN 978-3-031-57963-9
Editore: Springer Nature
DOI: 10.1007/978-3-031-57963-9

Thesis and dissertations (1)

Uncertainty in Reinforcement Learning and its Application to Scheduling Problems in Manufacturing

Autori: J. Golub, A. Faza, K. Shariatmadar, D. Moens
Pubblicato in: MSc dissertation, 2024
Editore: KU Leuven
DOI: 10.5281/zenodo.14223900

Book chapters (1)

Improving Metaheuristic Efficiency for Stochastic Optimization by Sequential Predictive Sampling

Autori: Noah Schutte, Krzysztof Postek, Neil Yorke-Smith
Pubblicato in: Lecture Notes in Computer Science, Integration of Constraint Programming, Artificial Intelligence, and Operations Research, Numero 25 May 2024, 2024, Pagina/e 158-175
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-60599-4_10