City Research Online

Article

Bennetot, A. ORCID: 0000-0001-8232-8728, Donadello, I. ORCID: 0000-0002-0701-5729, El Qadi El Haouari, A. ORCID: 0000-0002-7296-1252 , Dragoni, M. ORCID: 0000-0003-0380-6571, Frossard, T. ORCID: 0009-0005-6388-5672, Wagner, B. ORCID: 0009-0002-6747-1862, Sarranti, A. ORCID: 0000-0002-1085-8428, Tulli, S. ORCID: 0000-0002-6826-370X, Trocan, M. ORCID: 0000-0001-6241-0126, Chatila, R. ORCID: 0000-0001-7822-0634, Holzinger, A. ORCID: 0000-0002-6786-5194, d'Avila Garcez, A. S. ORCID: 0000-0001-7375-9518 & Díaz-Rodríguez, N. ORCID: 0000-0003-3362-9326view all authors (2025). A Practical Tutorial on Explainable AI Techniques. ACM Computing Surveys, 57(2), pp. 1-44. doi: 10.1145/3670685

White, A., Saranti, M., d’Avila Garcez, A. ORCID: 0000-0001-7375-9518 , Hope, T. M. H., Price, C. J. & Bowman, H.view all authors (2024). Predicting recovery following stroke: Deep learning, multimodal data and feature selection using explainable AI. NeuroImage: Clinical, 43, article number 103638. doi: 10.1016/j.nicl.2024.103638

Ngan, K. H., Mansouri-Benssassi, E., Phelan, J. , Townsend, J. & Garcez, A. D.view all authors (2024). From explanation to intervention: Interactive knowledge extraction from Convolutional Neural Networks used in radiology. PLoS ONE, 19(4), article number e0293967. doi: 10.1371/journal.pone.0293967

Garcez, A. D. & Lamb, L. C. (2023). Neurosymbolic AI: the 3rd wave. Artificial Intelligence Review, 56(11), pp. 12387-12406. doi: 10.1007/s10462-023-10448-w

White, A., Ngan, K. H., Phelan, J. , Ryan, K., Afgeh, S. S., Reyes-Aldasoro, C. C. ORCID: 0000-0002-9466-2018 & d’Avila Garcez, A.view all authors (2023). Contrastive counterfactual visual explanations with overdetermination. Machine Learning, 112(9), pp. 3497-3525. doi: 10.1007/s10994-023-06333-w

Caffo, B. S., D'Asaro, F. A., d'Avila Garcez, A. S. & Raffinetti, E.view all authors (2022). Editorial: Explainable artificial intelligence models and methods in finance and healthcare. Frontiers in Artificial Intelligence, 5, doi: 10.3389/frai.2022.970246

Percy, C., Dragicevic, S., Sarkar, S. & d’Avila Garcez, A.view all authors (2022). Accountability in AI: From principles to industry-specific accreditation. AI Communications, 34(3), pp. 181-196. doi: 10.3233/aic-210080

Badreddine, S., d'Avila Garcez, A. S., Serafini, L. & Spranger, M.view all authors (2022). Logic Tensor Networks. Artificial Intelligence, 303, article number 103649. doi: 10.1016/j.artint.2021.103649

Tran, S. N., Garcez, A., Weyde, T. ORCID: 0000-0001-8028-9905 , Yin, J., Zhang, Q. ORCID: 0000-0003-0982-2986 & Karunanithi, M.view all authors (2020). Sequence Classification Restricted Boltzmann Machines With Gated Units. IEEE Transactions on Neural Networks and Learning Systems, 31(11), pp. 4806-4815. doi: 10.1109/tnnls.2019.2958103

White, A. & d'Avila Garcez, A. S. (2020). Measurable counterfactual local explanations for any classifier. Frontiers in Artificial Intelligence and Applications, 325, pp. 2529-2535. doi: 10.3233/FAIA200387

Garcez, A., Gori, M., Lamb, L. C. , Serafini, L., Spranger, M. & Tran, S. N.view all authors (2019). Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. Journal of Applied Logics, 6(4), pp. 611-631.

Tran, S.N. & d'Avila Garcez, A. S. (2018). Deep Logic Networks: Inserting and Extracting Knowledge from Deep Belief Networks. IEEE Transactions on Neural Networks and Learning Systems, 29(2), pp. 246-258. doi: 10.1109/tnnls.2016.2603784

Howe, J. M., Mota, E.D. & Garcez, A. (2017). Inductive learning in Shared Neural Multi-Spaces. CEUR Workshop Proceedings, 2003,

Tran, S. N., Cherla, S., Garcez, A. & Weyde, T.view all authors (2017). The Recurrent Temporal Discriminative Restricted Boltzmann Machines. CoRR,

Sarkar, S., Weyde, T., Garcez, A. , Slabaugh, G. G., Dragicevic, S. & Percy, C.view all authors (2016). Accuracy and interpretability trade-offs in machine learning applied to safer gambling. CEUR Workshop Proceedings, 1773,

Ali, H., Tran, S. N., Benetos, E. & d'Avila Garcez, A. S.view all authors (2016). Speaker recognition with hybrid features from a deep belief network. Neural Computing and Applications, 29(6), pp. 13-19. doi: 10.1007/s00521-016-2501-7

Cherla, S., Tran, S.N., Weyde, T. & Garcez, A.view all authors (2016). Generalising the Discriminative Restricted Boltzmann Machine. pp. 111-119. doi: 10.1007/978-3-319-68612-7_13

Forechi, A., De Souza, A.F., Neto, J.D.O. , de Aguiar, E., Badue, C., Garcez, A. & Oliveira-Santos, T.view all authors (2016). Fat-Fast VG-RAM WNN: A high performance approach. NEUROCOMPUTING, 183, pp. 56-69. doi: 10.1016/j.neucom.2015.06.104

Percy, C., Garcez, A., Dragicevic, S. , França, M. V. M., Slabaugh, G. G. & Weyde, T.view all authors (2016). The Need for Knowledge Extraction: Understanding Harmful Gambling Behavior with Neural Networks. Frontiers in Artificial Intelligence and Applications, 285, pp. 974-981. doi: 10.3233/978-1-61499-672-9-974

Besold, T. R., Kuehnberger, K-U., Garcez, A. , Saffiotti, A., Fischer, M. H. & Bundy, A.view all authors (2015). Anchoring Knowledge in Interaction: Towards a Harmonic Subsymbolic/Symbolic Framework and Architecture of Computational Cognition. Lecture Notes in Computer Science, 9205, pp. 35-45. doi: 10.1007/978-3-319-21365-1_4

Perotti, A., Boella, G. & Garcez, A. (2014). Runtime Verification Through Forward Chaining. Electronic Proceedings in Theoretical Computer Science, 169, pp. 68-81. doi: 10.4204/eptcs.169.8

Ali, H., D'Avila Garcez, A.S., Tran, S.N. , Zhou, X. & Iqbal, K.view all authors (2014). Unimodal late fusion for NIST i-vector challenge on speaker detection. Electronics Letters, 50(15), pp. 1098-1100. doi: 10.1049/el.2014.1207

França, M. V. M., Zaverucha, G. & Garcez, A. (2014). Fast relational learning using bottom clause propositionalization with artificial neural networks. Machine Learning, 94(1), pp. 81-104. doi: 10.1007/s10994-013-5392-1

Sigtia, S., Benetos, E., Boulanger-Lewandowski, N. , Weyde, T., Garcez, A. & Dixon, S.view all authors (2014). A Hybrid Recurrent Neural Network For Music Transcription. CoRR, 14(11), article number 1623.

Tran, S. & Garcez, A. (2014). Low-cost representation for restricted Boltzmann machines. Lecture Notes in Computer Science, 8834, pp. 69-77. doi: 10.1007/978-3-319-12637-1_9

d'Avila Garcez, A. S., Gabbay, D. M. & Lamb, L. C. (2014). A neural cognitive model of argumentation with application to legal inference and decision making. Journal of Applied Logic, 12(2), pp. 109-127. doi: 10.1016/j.jal.2013.08.004

Borges, Rafael, Garcez, A. & Lamb, L. C. (2011). Learning and Representing Temporal Knowledge in Recurrent Networks. IEEE Transactions on Neural Networks, 22(12), pp. 2409-2421. doi: 10.1109/tnn.2011.2170180

Guillame-Bert, M., Broda, K. & Garcez, A. (2010). First-order logic learning in artificial neural networks. International Joint Conference on Neural Networks (IJCNN 2010), doi: 10.1109/IJCNN.2010.5596491

Garcez, A., Lamb, L. C. & Gabbay, D. M. (2007). Connectionist modal logic: Representing modalities in neural networks. Theoretical Computer Science, 371(1-2), pp. 34-53. doi: 10.1016/j.tcs.2006.10.023

Garcez, A., Gabbay, D. M., Ray, O. & Woods, J.view all authors (2007). Abductive reasoning in neural-symbolic learning systems. Topoi: An International Review of Philosophy, 26(1), pp. 37-49. doi: 10.1007/s11245-006-9005-5

Garcez, A., Gabbay, D. M. & Lamb, L. C. (2005). Value-based argumentation frameworks as neural-symbolic learning systems. Journal of Logic and Computation, 15(6), pp. 1041-1058. doi: 10.1093/logcom/exi057

Garcez, A. (2005). Fewer epistemological challenges for connectionism. Lecture Notes in Computer Science, 3526, pp. 289-325. doi: 10.1007/11494645_18

Garcez, A., Broda, K. & Gabbay, D. M. (2001). Symbolic knowledge extraction from trained neural networks: A sound approach. Artificial Intelligence, 125(1-2), pp. 153-205. doi: 10.1016/S0004-3702(00)00077-1

Garcez, A. & Zaverucha, G. (1999). The connectionist inductive learning and logic programming system. Applied Intelligence Journal, 11(1), pp. 59-77. doi: 10.1023/a:1008328630915

Book Section

Ngan, K. H., d'Avila Garcez, A., Knapp, K. , Appelboam, A. & Reyes-Aldasoro, C. C. ORCID: 0000-0002-9466-2018view all authors (2020). A machine learning approach for Colles' fracture treatment diagnosis. In: Medical Image Understanding and Analysis: 24th Annual Conference, MIUA 2020, Oxford, UK, July 15-17, 2020, Proceedings. Communications in Computer and Information Science (1248). (pp. 319-330). Cham: Springer. doi: 10.1007/978-3-030-52791-4_25

Perotti, A., d'Avila Garcez, A. S. & Boella, G. (2015). Neural-Symbolic Monitoring and Adaptation. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2015). (pp. 1-8). IEEE. doi: 10.1109/IJCNN.2015.7280713

Cherla, S., Weyde, T., Garcez, A. & Pearce, M.view all authors (2013). A Distributed Model For Multiple-Viewpoint Melodic Prediction. In: de Souza Britto Jr, A., Gouyon, F. & Dixon, S. (Eds.), Proceedings of the 14th International Society for Music Information Retrieval Conference. (pp. 15-20). International Society for Music Information Retrieval.

de Penning, L., Garcez, A., Lamb, L. C. & Meyer, J-J. C.view all authors (2011). A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning. In: Proceedings of the Twenty-Second international joint conference on Artificial Intelligence. (pp. 1653-1658). International Joint Conferences on Artificial Intelligence. doi: 10.5591/978-1-57735-516-8/IJCAI11-278

Conference or Workshop Item

Su, Q., Kloukinas, C. ORCID: 0000-0003-0424-7425 & d’Avila Garcez, A. ORCID: 0000-0001-7375-9518 (2024). FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series. In: 2024 International Joint Conference on Neural Networks (IJCNN). 2024 International Joint Conference on Neural Networks (IJCNN), 30 Jun - 5 Jul 2024, Yokohama, Japan. doi: 10.1109/ijcnn60899.2024.10651481

Silkar, D., d'Avila Garcez, A. ORCID: 0000-0001-7375-9518, Bloomfield, R. ORCID: 0000-0002-2050-6151 , Weyde, T. ORCID: 0000-0001-8028-9905, Peeroo, K. ORCID: 0000-0001-8601-4750, Singh, N., Hutchinson, M., Laksono, D. ORCID: 0000-0002-8503-5274 & Reljan-Delaney, M. ORCID: 0009-0000-8722-9323view all authors (2024). The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Others. In: Computer Graphics & Visual Computing (CGVC). CGVC, 12-13 Sep 2024, London, United Kingdom. doi: 10.2312/cgvc.20241239

Tran, S. N. & Garcez, A. (2023). Neurosymbolic Reasoning and Learning with Restricted Boltzmann Machines. In: Williams, B., Chen, Y. & Neville, J. (Eds.), Proceedings of the AAAI Conference on Artificial Intelligence. 37th AAAI Conference on Artificial Intelligence, 7-14 Feb 2023, Washington, D.C., USA. doi: 10.1609/aaai.v37i5.25806

Carvalho, B. W., d’Avila Garcez, A. S. ORCID: 0000-0001-7375-9518 & Lamb, L. C. (2023). Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Paper. In: CEUR Workshop Proceedings. Thinking Fast and Slow and Other Cognitive Theories in AI a AAAI 2022 Fall Symposium, 17-19 Nov 2022, Arlington, Virginia, US.

Ngan, K. H., Phelan, J., Mansouri-Benssassi, E. , Townsend, J. & d'Avila Garcez, A. S.view all authors (2023). Closing the Neural-Symbolic Cycle: Knowledge Extraction, User Intervention and Distillation from Convolutional Neural Networks. In: CEUR Workshop Proceedings. 17th International Workshop on Neural-Symbolic Learning and Reasoning, 3-5 Jul 2023, Siena, Italy.

Stromfelt, H., Dickens, L., d'Avila Garcez, A. ORCID: 0000-0001-7375-9518 & Russo, A.view all authors (2022). Formalizing Consistency and Coherence of Representation Learning. In: Koyejo, S., Mohamed, S., Agarwal, A. , Belgrave, D., Cho, K. & Oh, A.view all authors (Eds.), Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022. Neural Information Processing Systems, 28 Nov - 9 Dec 2022, New Orleans, USA.

Apperly, I., Bundy, A., Cohn, A. , Colton, S., Cussens, J., d'Avila Garcez, A. S., Hahn, U., Jamnik, M., Jay, C., Mareschal, D., Sammut, C., Schmid, U., Seed, A., Stahl, B., Steedman, M. & Tamaddoni-Nezhad, A.view all authors (2022). Preface. In: CEUR Workshop Proceedings. 3rd Human-Like Computing Workshop (HLC 2022), 28-30 Sep 2022, Windsor, United Kingdom.

Ngan, K. H., Garcez, A. & Townsend, J. (2022). Extracting Meaningful High-Fidelity Knowledge from Convolutional Neural Networks. In: 2022 International Joint Conference on Neural Networks (IJCNN). 2022 International Joint Conference on Neural Networks (IJCNN), 18-23 Jul 2022, Padua, Italy. doi: 10.1109/ijcnn55064.2022.9892194

Wagner, B. & d'Avila Garcez, A. S. ORCID: 0000-0001-7375-9518 (2022). Neural-Symbolic Reasoning Under Open-World and Closed-World Assumptions. In: CEUR Workshop Proceedings. AAAI 2022 Spring Symposium on Machine Learning and Knowledge Engineering for Hybrid Intelligence (AAAI-MAKE 2022), 21-23 Mar 2022, California, USA.

Stromfelt, H., Dickens, L., d'Avila Garcez, A. S. & Russo, A.view all authors (2021). Coherent and Consistent Relational Transfer Learning with Auto-encoders. In: Proceedings of the 15th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2021). 15th International Workshop on Neural-Symbolic Learning and Reasoning, 25-27 Oct 2021, Virtual event.

d’Avila Garcez, A. & Jimenez-Ruiz, E. ORCID: 0000-0002-9083-4599 (2021). Preface. In: Proceedings of the 15th International Workshop on Neural-Symbolic Learning and Reasoning as part of the 1st International Joint Conference on Learning & Reasoning (IJCLR 2021). 15th International Workshop on Neural-Symbolic Learning and Reasoning, 25-27 Oct 2021, Online.

Wagner, B. & d'Avila Garcez, A. S. ORCID: 0000-0001-7375-9518 (2021). Neural-symbolic integration for fairness in AI. In: CEUR Workshop Proceedings. AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), 22-24 Mar 2021, California, USA.

Philps, D., Garcez, A. & Weyde, T. ORCID: 0000-0001-8028-9905 (2019). Making Good on LSTMs' Unfulfilled Promise. Paper presented at the NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, 13 Dec 2019, Vancouver, Canada.

Mota, E., Howe, J. M. ORCID: 0000-0001-8013-6941, Schramm, A. & d'Avila Garcez, A. S.view all authors (2019). Efficient Predicate Invention using Shared NeMuS. In: 14th International Workshop on Neural-Symbolic Learning and Reasoning. 14th International Workshop on Neural-Symbolic Learning and Reasoning, 10 - 16 August 2019, Macau, China.

Donadello, I., Serafini, L. & d'Avila Garcez, A. S. (2017). Logic tensor networks for semantic image interpretation. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. IJCAI 2017, 19-25 Aug 2017, Melbourne, Australia.

Russell, A. J., Benetos, E. & Garcez, A. (2017). On the Memory Properties of Recurrent Neural Models. Paper presented at the 2017 International Joint Conference on Neural Networks, 14-19 May 2017, Anchorage, USA.

Sigtia, S., Benetos, E., Boulanger-Lewandowski, N. , Weyde, T., Garcez, A. & Dixon, S.view all authors (2015). A Hybrid Recurrent Neural Network For Music Transcription. Paper presented at the 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015, 19-04-2015 - 24-04-2015, Brisbane, Australia.

França, M. V. M., Zaverucha, G. & Garcez, A. (2015). Neural Relational Learning Through Semi-Propositionalization of Bottom Clauses. Paper presented at the 2015 AAAI Spring Symposium Series, 23-03-2015 - 25-03-2015, Stanford University, USA.

Garcez, A., Besold, T. R., Raedt, L. , Foldiak, P., Hitzler, P., Icard, T., Kuhnberger, K-U., Lamb, L. C., Miikkulainen, R. & Silver, D. L.view all authors (2015). Neural-Symbolic Learning and Reasoning: Contributions and Challenges. Paper presented at the 2015 AAAI Spring Symposium Series, 23-03-2015 - 25-03-2015, Stanford University, USA.

Tran, S., Benetos, E. & Garcez, A. (2014). Learning motion-difference features using Gaussian restricted Boltzmann machines for efficient human action recognition. Paper presented at the 2014 International Joint Conference on Neural Networks (IJCNN), 06-07-2014 - 11-07-2014, Beijing, China. doi: 10.1109/IJCNN.2014.6889945

Sigtia, S., Benetos, E., Cherla, S. , Weyde, T., Garcez, A. & Dixon, S.view all authors (2014). An RNN-based Music Language Model for Improving Automatic Music Transcription. In: Wang, H-M, Yang, Y-H & Lee, JH (Eds.), http://www.terasoft.com.tw/conf/ismir2014//proceedings%5CISMIR2014_Proceedings.pdf. 15th International Society for Music Information Retrieval Conference (ISMIR), 27-10-2014 - 31-10-2014, Taipei, Taiwan.

Cherla, S., Weyde, T., Garcez, A. & Pearce, M.view all authors (2013). Learning Distributed Representations for Multiple-Viewpoint Melodic Prediction. Paper presented at the 14th International Society for Music Information Retrieval Conference, 4 - 8 Nov 2013, Curtiba, PR, Brazil.

Garcez, A. (2010). Neurons and symbols: a manifesto. Paper presented at the Dagstuhl Seminar Proceedings 10302. Learning paradigms in dynamic environments, 25 - 30 July 2010, Dagstuhl, Germany.

Komendantskaya, E., Broda, K. & Garcez, A. (2010). Using inductive types for ensuring correctness of neuro-symbolic computations. Paper presented at the 6th Conference on Computability in Europe, CiE 2010, 30 June - 4 July 2010, Ponta Delgada, Portugal.

Child, C. H. T., Stathis, K. & Garcez, A. (2007). Learning to Act with RVRL Agents. Paper presented at the 14th RCRA Workshop, Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion, Jul 2007, Rome, Italy.

Broda, K., Garcez, A. & Gabbay, D. M. (2005). Metalevel priorities and neural networks. Paper presented at the Workshop on the Foundations of Connectionist-Symbolic Integration ECAI2000, 20 - 25 August 2005, Berlin.

Hitzler, P., Bader, S. & Garcez, A. (2005). Ontology learning as a use-case for neural-symbolic integration. Paper presented at the IJCAI Workshop on Neural-Symbolic Learning and Reasoning NeSy05, 1 August 2005, Edinburgh.

Report

Renou, L. & d'Avila Garcez, A. S. (2008). Rule Extraction from Support Vector Machines: A Geometric Approach. Technical Report (TR/2008/DOC/01). Department of Computing, City University London: .

d'Avila Garcez, A. S., Hitzler, P. & Tamburrini, G. (2006). Proceedings of ECAI International Workshop on Neural-Symbolic Learning and reasoning NeSy 2006 (TR/2006/DOC/02). .

Dafas, P. & d'Avila Garcez, A. S. (2005). Applied temporal Rule Mining to Time Series (TR/2006/DOC/01). .

d'Avila Garcez, A. S. (2005). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning NeSy 2005 (TR/2005/DOC/01). .

Garcez, A., Gabbay, D. M. & Lamb, L. C. (2004). Argumentation Neural Networks: Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems (TR/2004/DOC/01). .

Garcez, A. & Gabbay, D. M. (2003). Fibring Neural Networks (TR/2003/SEG/03). .

Garcez, A., Spanoudakis, G. & Zisman, A. (2003). Proceedings of ACM ESEC/FSE International Workshop on Intelligent Technologies for Software Engineering WITSE03 (TR/2003/DOC/01). .

Working Paper

Tran, S. N. & Garcez, A. (2014). Adaptive Feature Ranking for Unsupervised Transfer Learning. .