Transparent, Reliable and Unbiased Smart Tool for AI

Información del proyecto

TRUST-AI

Identificador del acuerdo de subvención: 952060

DOI

10.3030/952060

Proyecto cerrado

Fecha de la firma de la CE 4 Junio 2020

Fecha de inicio 1 Octubre 2020

Fecha de finalización 31 Marzo 2025

Financiado con arreglo a

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Coste total

€ 3 996 418,75

Aportación de la UE

€ 3 996 418,75

Coordinado por

INESC TEC - INSTITUTO DE ENGENHARIADE SISTEMAS E COMPUTADORES, TECNOLOGIA E CIENCIA
Portugal

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Documents, reports (20)

Management Report

This deliverable concerns a status report on the technical achievements of TRUST in the first nine months of the projects A brief description of the development of each task will be provided including documentation of procedures screenshots preliminary results and identified risks

Data management plan V2
Final validation of the learned explainable AI models (online retail)

In this deliverable, a final validation of the proposed approach will be provided. The results and final conclusions of the online retail use case will be described together with lessons learned and recommendations for future developments.

Final validation of the learned explainable AI models for the energy use case

In this deliverable, a final validation of the proposed approach will be provided. The results and final conclusions of the energy use case will be described together with lessons learned and recommendations for future developments.

Saliency measures for identifying causally variables of explanations

This report will present the saliency measures and code for identifying causally relevant variables of humanlike explanations The relevant variables are those to be considered during the discovery and communication of causal explanations These variables will be formalised and measurable in terms of their specificity insensitivity proximity and other characteristics known to be preferred by humans

User studies on the realization of explanations

The deliverable reports the result of the qualitative studies on the best way to present explanation content produced in WP3 and provides recommendations for Task 22

Communication & Dissemination report

This deliverable will present a final status on the achievement of the project objectives in terms of communication and dissemination. The report will refer to the KPIs proposed on Deliverable D8.1.

Evaluation by human observers of different explainability formats

This deliverable reports the results of the evaluation of explainability performed in Task2.3.

Final validation of the learned explainable AI models (healthcare)

In this deliverable, a final validation of the proposed approach will be provided. The results and final conclusions of the healthcare use case will be described together with lessons learned and recommendations for future developments.

Data management plan V3
Dialog WP4-WP3

In this deliverable, the results of the interaction between WP4 and WP3 will be presented. The final outcome is the generation of explainable expressions by iterated dialog with the user in the proposed toy problems.

Exploitation Plan

This report described the future exploration of the framework, detailed in Task 8.3.Partners will consolidate all relevant findings, identify risks and evaluate the potential applicability of TRUST components in different sectors, covering many aspects of AI.

Communication & Dissemination update

This deliverable will present an updated status of the CDP, reporting the achievements obtained for each KPI and possible necessary changes to the plan.

Framework requirements document

This deliverable will describe the functional and nonfunctional requirements of the framework as well as the interactions and dependencies between the building blocks The use case needs will also be detailed and reported in this document ensuring that the framework is adequate to different problems and sectors

Communication & Dissemination plan

This report will present the Communication Dissemination Plan of TRUST where the strategy to raise public awareness about the project outcomes will be detailed and scheduled In addition to academic publications and conferences the plan includes events promotion participation in working groups and online forums and educational content creation such as courseware and webinars The plan will include KPIs and their target values as well as the Partner responsible for each communicationdissemination method

Evaluation with healthcare experts of learned models

This deliverable concerns a formal validation of the AI models developed for the first simplified version of the healthcare problem These models will be designed by NWOI and validated by medical experts from LUMC The report will present the first insights on the models results and suggestions for modifications

Initial validation of the explainable AI models from business experts

This deliverable concerns a formal validation of the AI models developed for the first simplified version of the online retail problem These models will be designed by LTP and validated by practitioners from Sonae INESC will coordinate the development and validation process

Data management plan

This deliverable presents the Data Management Plan of TRUSTAI detailing the types of data generatedcollected how it will be exploited protected and the standards to be considered

Framework validation

This deliverable consolidates the final conclusions from the use cases and describes the primary outcomes of TRUST framework. Recommendations for future extensions will also be included.

Initial validation of the explainable AI models from energy experts

This deliverable concerns a formal validation of the AI models developed for the first simplified version of the energy problem These models will be designed by POLIS21 and validated by practitioners from the industry

Other (2)

Automated medical image analysis learning techniques

This deliverable concerns the automated image analysis learning techniques integrated with TRUST blocks.

Project website

This deliverable will present the specification, organization and features of TRUST-AI website. The DNS, URL to access and screenshots on each page will also be presented.

Publicaciones

Conference proceedings (16)

Coefficient mutation in the gene-pool optimal mixing evolutionary algorithm for symbolic regression

Autores: M. Virgolin and P.A.N. Bosman
Publicado en: GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2022, Página(s) 2289–2297
Editor: ACM
DOI: 10.1145/3520304.3534036

Symbolic Pricing Policies for Attended Home Delivery - the Case of a European Retailer

Autores: Miguel Lunet, Daniela Fernandes, Fábio Neves-Moreira, Pedro Amorim
Publicado en: GECCO '25: Genetic and Evolutionary Computation Conference, 2025
Editor: Digital Library

Multi-objective Genetic Programming for Explainable Reinforcement Learning

Autores: Videau, Mathurin; Ferreira Leite, Alessandro; Teytaud, Olivier; Schoenauer, Marc
Publicado en: EUROGP - 25th European Conference on Genetic Programming, part of EvoStar 2022, Edición 25, 2022, Página(s) pp.278-293, ISBN 978-3-031-02055-1
Editor: Springer Verlag
DOI: 10.1007/978-3-031-02056-8_18

Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis

Autores: Eduard Barbu, Marharytha Domnich, Raul Vicente, Nikos Sakkas, André Morim
Publicado en: The 2nd World Conference on eXplainable Artificial Intelligence (xAI 2024), July 17-19, 2024 - Valletta, Malta, 2024
Editor: Springer
DOI: 10.48550/arxiv.2405.11958

Multi-modal multi-objective model-based genetic programming to find multiple diverse high-quality models

Autores: Sijben, Evi; Alderliesten, Tanja; Bosman, Peter
Publicado en: GECCO '22: Genetic and Evolutionary Computation Conference, 2022, ISBN 978-1-4503-9237-2
Editor: Association for Computing Machinery, New York, NY, United States
DOI: 10.48550/arxiv.2203.13347

Memetic Semantic Genetic Programming for Symbolic Regression

Autores: Alessandro Leite and Marc Schoenauer
Publicado en: 26th EuroGP - Part of EvoStar 2023, Edición 26, 2023, Página(s) 198–212, ISBN 978-3-031-29572-0
Editor: Springer Verlag LNCS-13986
DOI: 10.1007/978-3-031-29573-7_13

A Guide for Practical Use of ADMG Causal Data Augmentation

Autores: Poinsot, Audrey; Leite, Alessandro
Publicado en: Workshop on the pitfalls of limited data and computation for Trustworthy ML, ICLR 2023, 2023
Editor: OpenReview
DOI: 10.48550/arxiv.2304.01237

Explanatory World Models via Look Ahead Attention for Credit Assignment

Autores: Oriol Corcoll and Raul Vicente
Publicado en: Edición 26403498, 2022, ISSN 2640-3498
Editor: Proceedings of Machine Learning Research

Function Class Learning with Genetic Programming: Towards Explainable Meta Learning for Tumor Growth Functionals

Autores: Evi Sijben, Jeroen Jansen, Peter Bosman, Tanja Alderliesten
Publicado en: Proceedings of the Genetic and Evolutionary Computation Conference, 2024, Página(s) 1354-1362
Editor: ACM
DOI: 10.1145/3638529.3654145

Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning

Autores: Labash, Aqeel; Fletzer, Florian; Majoral, Daniel; Vicente, Raul
Publicado en: ICML'23: Proceedings of the 40th International Conference on Machine Learning, Edición 18, 2023
Editor: JMLR.org
DOI: 10.48550/arxiv.2307.12143

COIN: Counterfactual inpainting for weakly supervised semantic segmentation for medical images

Autores: Dmytro Shvetsov, Joonas Ariva, Marharyta Domnich, Raul Vicente, Dmytro Fishman
Publicado en: The 2nd World Conference on eXplainable Artificial Intelligence (xAI 2024), July 17-19, 2024 - Valletta, Malta, 2024
Editor: Springer
DOI: 10.48550/arxiv.2404.12832

Learning symbolic expressions to solve multi-period time slot pricing vehicle routing problems

Autores: Fábio Neves-Moreira, Daniela Fernandes, Miguel Lunet, Pedro Amorim
Publicado en: IJCAI 2024 - International Joint Conference on Artificial Intelligence, Jeju, South Korea, 2024
Editor: IJCAI

Deep learning-based auto-segmentation of paraganglioma for growth monitoring

Autores: E.M.C. Sijben, J.C. Jansen, P.A.N. Bosman (Peter), and T. Alderliesten
Publicado en: Proceedings Volume 12929, Medical Imaging 2024: Image Perception, Observer Performance, and Technology Assessment, 2024, Página(s) 1292916
Editor: SPIE
DOI: 10.1117/12.3006413

Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherence

Autores: Marharyta Domnich, Raul Vicente
Publicado en: The 2nd World Conference on eXplainable Artificial Intelligence (xAI 2024), July 17-19, 2024 - Valletta, Malta, 2024
Editor: Springer
DOI: 10.48550/arxiv.2404.12810

Real time Data and Application Sharing and Collaboration for the Building Energy Domain

Autores: N. Sakkas, M. Papadopoulou, D. Sakkas
Publicado en: WDBE 2021, 2021
Editor: World of Digital Built Environment WDBE 2021

Evolvability degeneration in multi-objective genetic programming for symbolic regression

Autores: Dazhuang Liu, Marco Virgolin, Tanja Alderliesten, Peter A. N. Bosman
Publicado en: GECCO '22: Genetic and Evolutionary Computation Conference, 2022
Editor: Association for Computing Machinery, New York, NY, United States
DOI: 10.1145/3512290.3528787

Peer reviewed articles (17)

Improving asset management in capital-intensive industries: Case study of a Portuguese water utility

Autores: Mariana Casalta, Flávia Barbosa, Luciana Yamada, Lígia B. Ramos
Publicado en: Utilities Policy, Edición 91, 2024, Página(s) 101822, ISSN 0957-1787
Editor: Pergamon Press Ltd.
DOI: 10.1016/j.jup.2024.101822

Mind the gap: challenges of deep learning approaches to Theory of Mind

Autores: Aru, Jaan; Labash, Aqeel; Corcoll, Oriol; Vicente, Raul
Publicado en: Artificial Ingtelligence Review, Edición 3, 2023, ISSN 0269-2821
Editor: Kluwer Academic Publishers
DOI: 10.1007/s10462-023-10401-x

Learning efficient in-store picking strategies to reduce customer encounters in omnichannel retail

Autores: Fábio Neves-Moreira, Pedro Amorim
Publicado en: International Journal of Production Economics, 2024, ISSN 0925-5273
Editor: Elsevier BV
DOI: 10.1016/j.ijpe.2023.109074

Scheduling wagons to unload in bulk cargo ports with uncertain processing times

Autores: Cristiane Ferreira, Gonçalo Figueira, Pedro Amorim, Alexandre Pigatti
Publicado en: Computers & Operations Research, 2023, ISSN 0305-0548
Editor: Pergamon Press Ltd.
DOI: 10.1016/j.cor.2023.106364

Open data or open access? The case of building data.

Autores: Sakkas, N., Yfanti, S
Publicado en: Academia Letters, 2021, ISSN 2771-9359
Editor: Academia.edu
DOI: 10.20935/al3629

Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments

Autores: Marharyta Domnich, Julius Välja, Rasmus Moorits Veski, Giacomo Magnifico, Kadi Tulver, Eduard Barbu, Raul Vicente
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 39, 2025, Página(s) 16308-16316, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i15.33791

Memetic semantic boosting for symbolic regression

Autores: Alessandro Leite, Marc Schoenauer
Publicado en: Genetic Programming and Evolvable Machines, Edición 26, 2025, ISSN 1389-2576
Editor: Kluwer Academic Publishers
DOI: 10.1007/s10710-024-09506-1

Explainable Approaches for Forecasting Building Electricity Consumption

Autores: Nikos Sakkas, Sofia Yfanti,Pooja Shah, Nikitas Sakkas, Christina Chaniotakis, Costas Daskalakis, Eduard Barbu and Marharyta Domnich
Publicado en: Energies, 2023, ISSN 1996-1073
Editor: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/en16207210

Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

Autores: Stelzer, Florian; Röhm, André; Vicente, Raul; Fischer, Ingo; Yanchuk, Serhiy
Publicado en: Nature Communications, Edición 20411723, 2021, ISSN 2041-1723
Editor: Nature Publishing Group
DOI: 10.48550/arxiv.2011.10115

Technology Readiness Levels (TRLs) in the Era of Co-Creation

Autores: Sofia Yfanti, Nikos Sakkas
Publicado en: Applied System Innovation, 2024, ISSN 2571-5577
Editor: MDPI
DOI: 10.3390/asi7020032

A cooperative coevolutionary hyper-heuristic approach to solve lot-sizing and job shop scheduling problems using genetic programming

Autores: Yannik Zeiträg, José Rui Figueira, Gonçalo Figueira
Publicado en: International Journal of Production Research, 2024, ISSN 0925-5273
Editor: Elsevier BV
DOI: 10.1080/00207543.2023.2301044

Building data models and data sharing. Purpose, approaches, and a case study on explainable demand response

Autores: Nikos Sakkas, Christina Chaniotaki and Nikitas Sakkas
Publicado en: IOP Conference Series: Earth and Environmental Science, 2023, ISSN 1757-899X
Editor: IOP Science
DOI: 10.1088/1755-1315/1122/1/012066

Personalized choice model for forecasting demand under pricing scenarios with observational data—The case of attended home delivery

Autores: Özden Gür Ali, Pedro Amorim
Publicado en: International Journal of Forecasting, 2024, Página(s) 706-720, ISSN 0169-2070
Editor: Elsevier BV
DOI: 10.1016/j.ijforecast.2023.04.008

Quantifying Reinforcement-Learning Agent’s Autonomy, Reliance on Memory and Internalisation of the Environment

Autores: Anti Ingel, Abdullah Makkeh, Oriol Corcoll and Raul Vicente
Publicado en: Entropy, Edición 10994300, 2022, ISSN 1099-4300
Editor: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/e24030401

Interpretable Forecasting of Energy Demand in the Residential Sector

Autores: Nikos Sakkas; Sofia Yfanti; Costas Daskalakis; Eduard Barbu; Marharyta Domnich
Publicado en: Energies, Edición 1, 2021, ISSN 1996-1073
Editor: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/en14206568

Do Deep Reinforcement Learning Agents Model Intentions?

Autores: Tambet Matiisen; Aqeel Labash; Daniel Majoral; Jaan Aru; Raul Vicente
Publicado en: Stats, Vol 6, Iss 1, Pp 50-66 (2022), Edición 5, 2022, ISSN 2571-905X
Editor: MDPI
DOI: 10.3390/stats6010004

Drivers of and counterfactuals for the final energy and electricity consumption in EU industry

Autores: Sakkas, N., Athanasiou, N.
Publicado en: Academia Letters, Edición 27719359, 2021, ISSN 2771-9359
Editor: Academia.edu
DOI: 10.20935/al3451

Thesis and dissertations (4)

Genetic Programming Approaches for Solving Transportation Problems

Autores: Catarina Furtado Martins da Rocha Leite
Publicado en: 2022
Editor: University of Porto

Using Dimensionally Aware Genetic Programming to find interpretable Dispatching Rules for the Job Shop Scheduling Problem

Autores: Álvaro Manuel Festas Pereira da Silva
Publicado en: 2021
Editor: University of Porto

A generic scalable web platform for XAI algorithms

Autores: Luís Pedro Viana Ramos
Publicado en: 2022
Editor: University of Porto

Interface Design for Human-guided Explainable AI

Autores: João Rafael Gomes Varela
Publicado en: 2022
Editor: University of Porto

Book chapters (1)

Simultaneous Model-Based Evolution of Constants and Expression Structure in GP-GOMEA for Symbolic Regression

Autores: Johannes Koch, Tanja Alderliesten, Peter A. N. Bosman
Publicado en: Lecture Notes in Computer Science, Parallel Problem Solving from Nature – PPSN XVIII, 2024, Página(s) 238-255
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-70055-2_15