Search
photo of Artur d'Avila Garcez

Professor Artur d'Avila Garcez

Professor of Computer Science

School of Mathematics, Computer Science and Engineering Department of Computer Science

Contact details

Address

Professor Artur d'Avila Garcez A304A, College Building
City, University of London
Northampton Square
London EC1V 0HB
United Kingdom

About

Overview

Professor Artur Garcez is Director of the Research Centre for Machine Learning at City, University of London. He holds a PhD in Computing (2000) from Imperial College London. He is a Fellow of the British Computer Society (FBCS).

Professor Garcez has an established track record of research in Machine Learning, Neural Computation and Artificial Intelligence. He is president of the steering committee of the
Neural-Symbolic Learning and Reasoning Association, and founding course director of City's MSc in Data Science. He has co-authored two books: Neural-Symbolic Cognitive Reasoning, 2009, and Neural-Symbolic Learning Systems, 2002. His research has led to publications in the journals Behavioral & Brain Sciences, Theoretical Computer Science, Neural Computation, Machine Learning, Journal of Logic and Computation, IEEE Transactions on Neural Networks, Journal of Applied Logic, Artificial Intelligence, and Studia Logica, and the flagship AI and Neural Computation conferences AAAI, NIPS, IJCAI, IJCNN, AAMAS and ECAI.

Professor Garcez holds editorial positions with several scientific journals in the fields of Computational Logic and Artificial Intelligence, and has been Programme Committee member for several conferences, including IJCAI, IJCNN, NIPS and AAAI.

Qualifications

  1. PhD Computing, Imperial College London, United Kingdom, 2000
  2. MSc Systems Engineering and Computing, Federal University of Rio de Janeiro, Brazil, 1996
  3. MEng Computing Engineering, Pontifical Catholic University of Rio de Janeiro, Brazil, 1993

Employment

  1. Professor of Computer Science, City, University of London, 2015 – present

Memberships of professional organisations

  1. Fellow, British Computer Society (BCS)
  2. Member, IEEE Computer Society
  3. Member, AAAI (Association for the Advancement of Artificial Intelligence)
  4. Member, City & Guilds College Association, London, UK
  5. Member, Computability in Europe (CiE) Association

Research

Research Interests

- Neural-Symbolic Computation, Neural Networks and Applied Logic, Complex Networks
- Machine Learning, Integrating Robust Learning and Reasoning under Uncertainty
- Cognitive Agents and Intelligent Systems, Knowledge Extraction, Visual Information Processing
- Business Process Evolution, Requirements Engineering, Automated Software Engineering

Publications

Publications by category

Books (4)

  1. Garcez, A.S.D., Lamb, L.C. and Gabbay, D.M. (2009). Neural-Symbolic Cognitive Reasoning. Cognitive Technologies. Springer-Verlag New York Inc. ISBN 978-3-540-73245-7.
  2. Artemov, S., Barringer, H., Garcez, A., Lamb, L.C. and Woods, J. (2005). We Will Show Them! Essays in Honour of Dov Gabbay. College Pubns. ISBN 978-1-904987-11-6.
  3. Artemov, S., Barringer, H., Garcez, A., Lamb, L.C. and Woods, J. (2005). We Will Show Them! Essays in Honour of Dov Gabbay. College Pubns. ISBN 978-1-904987-26-0.
  4. Garcez, A.S.D., Broda, K. and Gabbay, D.M. (2002). Neural-symbolic learning systems: Foundations and Applications. Perspectives in Neural Computing. Springer Verlag. ISBN 978-1-85233-512-0.

Chapters (9)

  1. Perotti, A., Garcez, A.D. and Boella, G. (2015). Neural-symbolic monitoring and adaptation. IEEE.
  2. Garcez, A.D. and Lamb, L.C. (2012). Learning and Argumentation in Neural-Symbolic Computation. In Seel, N.M. (Ed.), Encyclopedia of the Sciences of Learning Not Avail. ISBN 978-1-4419-1427-9.
  3. Garcez, A.D. and Lamb, L.C. (2011). Cognitive Reasoning and Knowledge Representation. In Cutsuridis, V., Hussain, A. and Taylor, J.G. (Eds.), Perception-Action Cycle: Models, Algorithms and Hardware (p. 573). Springer Verlag. ISBN 978-1-4419-1451-4.
  4. de Penning, L., Garcez, A.D., Lamb, L.C. and Meyer, J.J. (2011). A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning. Proceedings of the Twenty-Second international joint conference on Artificial Intelligence (pp. 1653–1658). ISBN 978-1-57735-514-4.
  5. Garcez, A.D. (2007). Advances in Neural-Symbolic Learning Systems: Modal and Temporal Reasoning. In Hammer, B. and Hitzler, P. (Eds.), Perspectives of neural-symbolic integration Springer Verlag. ISBN 978-3-540-73953-1.
  6. Garcez, A.D. and Lamb, L.C. (2005). Neural-Symbolic Systems and The Case for Non-Classical Reasoning. In Artemov, S., Barringer, H., Garcez, A.D., Lamb, L.C. and Woods, J. (Eds.), We Will Show Them! Essays in Honour of Dov Gabbay College Pubns. ISBN 978-1-904987-11-6.
  7. Garcez, A.D. (2004). On Gabbay's Fibring Methodology for Bayesian and Neural Networks. In Gillies, D. (Ed.), Laws and models in science College Publications. ISBN 978-0-9543006-6-1.
  8. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2003). Neural-Symbolic Intuitionistic Reasoning. In Abraham, A., Köppen, M. and Franke, K. (Eds.), Frontiers in Artificial Intelligence and Applications IOS Press. ISBN 978-1-58603-394-1.
  9. Garcez, A.D., Zaverucha, G. and de Carvalho, L.A.V. (1997). Logic Programming and Inductive Learning in Artificial Neural Networks. In H, C., Reine, F. and Strohmaier, A. (Eds.), Knowledge Representation in Neural Networks (pp. 33–46). ISBN 978-3-931216-77-1.

Conference papers and proceedings (83)

  1. Wagner, B. and d'Avila Garcez, A. (2021). Neural-symbolic integration for fairness in AI.
  2. Charitou, C., Garcez, A.D. and Dragicevic, S. (2020). Semi-supervised GANs for Fraud Detection*. 2020 International Joint Conference on Neural Networks (IJCNN) 19-24 July.
  3. White, A. and D'Avila Garcez, A. (2020). Measurable counterfactual local explanations for any classifier.
  4. Ngan, K.H., Garcez, A.D., Knapp, K.M., Appelboam, A. and Reyes-Aldasoro, C.C. (2020). A Machine Learning Approach for Colles’ Fracture Treatment Diagnosis.
  5. Riveret, R., Tran, S. and Garcez, A.D.A. (2020). Neural-symbolic probabilistic argumentation machines.
  6. Philps, D., Garcez, A.D. and Weyde, T. (2019). Making Good on LSTMs' Unfulfilled Promise. NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy 8-14 December, Vancouver.
  7. Weyde, T., Philps, D. and d'Avila Garcez, A. (2018). Continual Learning Augmented Investment Decisions. 2018 NeurIPS Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy (FEAP-AI4Fin) 2-8 December, Montreal.
  8. Donadello, I., Serafini, L. and d'Avila Garcez, A. (2017). Logic Tensor Networks for Semantic Image Interpretation. Twenty-Sixth International Joint Conference on Artificial Intelligence 19-26 August.
  9. Russell, A.J., Benetos, E. and D'Avila Garcez, A. (2017). On the memory properties of recurrent neural models.
  10. Serafini, L., Donadello, I. and Garcez, A.D. (2017). Learning and reasoning in logic tensor networks. SAC 2017: Symposium on Applied Computing.
  11. Odense, S. and d’Avila Garcez, A. (2017). Extracting M of N Rules from Restricted Boltzmann Machines.
  12. Tran, S.N. and Garcez, A.D. (2016). Adaptive Transferred-profile Likelihood Learning. 2016 International Joint Conference on Neural Networks (IJCNN) 24-29 July.
  13. Sarkar, S., Weyde, T., Garcez, A.D.A., Slabaugh, G., Dragicevic, S. and Percy, C. (2016). Accuracy and interpretability trade-offs in machine learning applied to safer gambling.
  14. Percy, C., D'Avila Garcez, A.S., Dragicevic, S., França, M.V.M., Slabaugh, G. and Weyde, T. (2016). The need for knowledge extraction: Understanding harmful gambling behavior with neural networks.
  15. Yilmaz, O., D'Avila Garcez, A. and Silver, D. (2016). A proposal for common dataset in neural-symbolic reasoning studies.
  16. Serafini, L. and Garcez, A.D.A. (2016). Logic tensor networks: Deep learning and logical reasoning from data and knowledge.
  17. Cherla, S., Tran, S.N., Garcez, A.D. and Weyde, T. (2015). Discriminative learning and inference in the Recurrent Temporal RBM for melody modelling. 2015 International Joint Conference on Neural Networks (IJCNN) 12-17 July.
  18. Tran, S.N. and Garcez, A.D. (2015). Efficient representation ranking for transfer learning. 2015 International Joint Conference on Neural Networks (IJCNN) 12-17 July.
  19. Sigtia, S., Benetos, E., Boulanger-Lewandowski, N., Weyde, T., d'Avila Garcez, A.S. and Dixon, S. (2015). A hybrid recurrent neural network for music transcription. ICASSP 2015 - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 19-24 April.
  20. Garcez, A.D.A., Besold, T.R., De Raedt, L., Foldiak, P., Hitzler, P., Icard, T. … Silver, D.L. (2015). Neural-symbolic learning and reasoning: Contributions and challenges.
  21. França, M.V.M., Zaverucha, G. and Garcez, A.S.D.A. (2015). Neural relational learning through semi-propositionalization of bottom clauses.
  22. Perotti, A., Boella, G. and Garcez, A.D. (2015). Runtime Verification Through Forward Chaining.
  23. França, M.V.M., D'Avila Garcez, A.S. and Zaverucha, G. (2015). Relational knowledge extraction from neural networks.
  24. Tran, S.N., Benetos, E. and d'Avila Garcez, A. (2014). Learning motion-difference features using Gaussian restricted Boltzmann machines for efficient human action recognition. 2014 International Joint Conference on Neural Networks (IJCNN) 6-11 July.
  25. de Penning, L., d'Avila Garcez, A.S., Lamb, L.C., Stuiver, A. and Meyer, J.-.J.C. (2014). Applying Neural-Symbolic Cognitive Agents in Intelligent Transport Systems to reduce CO2 emissions. 2014 International Joint Conference on Neural Networks (IJCNN) 6-11 July.
  26. Perotti, A., d'Avila Garcez, A. and Boella, G. (2014). Neural Networks for Runtime Verification. 2014 International Joint Conference on Neural Networks (IJCNN) 6-11 July.
  27. Tran, S.N., Wolff, D., Weyde, T. and Garcez, A.D.A. (2014). Feature preprocessing with Restricted Boltzmann Machines for music similarity learning.
  28. Sigtia, S., Benetos, E., Cherla, S., Weyde, T., d’Avila Garcez, A.S. and Dixon, S. (2014). An RNN-based music language model for improving automatic music transcription.
  29. De Penning, L., D'Avila Garcez, A.S., Lamb, L.C. and Meyer, J.J.C. (2014). Neural-symbolic cognitive agents: Architecture, theory and application.
  30. Perotti, A., Boella, G. and D'Avila Garcez, A. (2014). Scalable process monitoring through rules and neural networks.
  31. França, M.V.M., Garcez, A.S.D. and Zaverucha, G. (2013). Relational knowledge extraction from attribute-value learners.
  32. Boella, G., Colombo Tosatto, S., Garcez, A.D., Genovese, V., Ienco, L. and van der Torre, L. (2011). Embedding Normative Reasoning into Neural-Symbolic Systems. IJCAI Workshop on Neural-Symbolic Learning and Reasoning NeSy11 July, Barcelona.
  33. Borges, R.V., Garcez, A.D., Lamb, L.C. and Nuseibeh, B. (2011). Learning to Adapt Requirements Specifications of Evolving Systems. 33rd International Conference on Software Engineering (ICSE'11), New Ideas and Emerging Results (NIER\ Track) May, Waikiki.
  34. Boella, G., Colombo Tosatto, S., Garcez, A.D., Genovese, V., Ienco, D. and van der Torre, L. (2011). A Neural-Symbolic System for Normative Agents. 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'11) May, Taipei.
  35. Garcez, A.D., Lamb, L.C. and Hitzler, P. (2011). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy11). Barcelona, Spain.
  36. Borges, R.V., Garcez, A.D., Lamb, L.C., Nuseibeh, B. and IEEE, (2011). Learning to Adapt Requirements Specifications of Evolving Systems (NIER Track).
  37. Garcez, A.D., de Penning, L., Lamb, L.C. and Meyer, J.J. (2010). An Integrated Neural Symbolic Cognitive Agent Architecture for Training and Assessment in Simulators. AAAI Workshop on Neural-Symbolic Learning and Reasoning NeSy'10 July, Georgia.
  38. Komendantskaya, E., Broda, K. and Garcez, A.D. (2010). Using Inductive Types for Ensuring Correctness of Neuro-Symbolic Computations. Computability in Europe CiE 2010 June, Ponta Delgada, Portugal.
  39. Boella, G., Colombo Tosatto, S., Garcez, A.D. and Genovese, V. (2010). On the Relationship between I-O Logic and Connectionism. Nonmonotonic Reasoning NMR 2010 Preferences and Norms workshop May, Toronto.
  40. Garcez, A.D. (2010). Neurons and Symbols: A Manifesto. Dagstuhl Seminar Proceedings 10302. Learning paradigms in dynamic environments Schloss Dagstuhl Leibniz-Zentrum fuer Informatik.
  41. Borges, R.V., Garcez, A.D. and Lamb, L.C. (2010). Representing, Learning and Extracting Temporal Knowledge from Neural Networks: A Case Study.
  42. Komendantskaya, E., Broda, K. and Garcez, A.D.A. (2010). Neuro-symbolic representation of logic programs defining infinite sets.
  43. Ryman-Tubb, N.F., Garcez, A.D. and IEEE, (2010). SOAR - Sparse Oracle-based Adaptive Rule Extraction: Knowledge extraction from large-scale datasets to detect credit card fraud.
  44. Guillame-Bert, M., Broda, K. and Garcez, A.D. (2010). First-order Logic Learning in Artificial Neural Networks.
  45. Ren, L. and Garcez, A.D.A. (2009). Symbolic knowledge extraction from support vector machines: A geometric approach.
  46. Garcez, A.D. and Hitzler, P. (2009). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy09). Pasadena, USA.
  47. Garcez, A.D. and Hitzler, P. (2008). Proceedings of ECAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy08). Patras, Greece.
  48. Borges, R.V., Lamb, L.C. and Garcez, A.D. (2007). Reasoning and Learning about Past Temporal Knowledge in Connectionist Models. 20th International Joint Conference on Neural Networks (IJCNN 2007) August, Orlando.
  49. Child, C., Stathis, K. and Garcez, A.D. (2007). Learning to Act with RVRL Agents. 14th RCRA Workshop, Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion July, Rome.
  50. Lamb, L.C., Borges, R.V. and Garcez, A.D. (2007). A Connectionist Cognitive Model for Temporal Synchronisation and Learning. 22nd National Conference on Artificial Intelligence (AAAI 2007) July, Vancouver.
  51. Borges, R.V., Lamb, L.C. and Garcez, A.D. (2007). Towards Reasoning about the Past in Neural-Symbolic Systems. IJCAI Workshop on Neural-Symbolic Learning and Reasoning NeSy07 January, Hyderabad, India.
  52. Garcez, A.D., Hitzler, P. and Tamburrini, G. (2007). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy07). Hyderabad, India.
  53. Borges, R.V., Lamb, L.C. and Garcez, A.D. (2006). Combining Architectures for Temporal Learning in Neural-Symbolic Systems. 6th International Conference on Hybrid Intelligent Systems ((HIS'06)) December.
  54. Ray, O. and Garcez, A.D. (2006). Towards the Integration of Abduction and Induction in Artificial Neural Networks. ECAI Workshop on Neural-Symbolic Learning and Reasoning NeSy06 August, Riva del Garda, Italy.
  55. Carneiro, R., Dias, S.S., Fardin Jr, D., Oliveira, H., Garcez, A.D. and de Souza, A.F. (2006). Improving VG-RAM Neural Network Performance using Knowledge Correlation. 13th International Conference on Neural Information Processing (ICONIP'06) Hong Kong.
  56. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2006). A Connectionist Model for Constructive Modal Reasoning. In Advances in Neural Information Processing Systems 18 (NIPS 2005) Vancouver.
  57. Garcez, A.D., Hitzler, P. and Tamburrini, G. (2006). Proceedings of ECAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy06). Trento, Italy.
  58. Hitzler, P., Bader, S. and Garcez, A.D. (2005). Ontology Learning as a Use-Case for Neural-Symbolic Integration. IJCAI Workshop on Neural-Symbolic Learning and Reasoning NeSy05 August, Edinburgh.
  59. Garcez, A.D. (2005). Fewer Epistemological Challenges for Connectionism. Computability in Europe 2005: New Computational Paradigms Amsterdam.
  60. Bader, S. and Garcez, A.D. (2005). Computing First Order Logic Programs by Fibring Artificial Neural Networks. 18th International FLAIRS Conference Florida.
  61. Garcez, A.D., Elman, J. and Hitzler, P. (2005). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning (NeSy05). Edinburgh, Scotland.
  62. Rodrigues, O., Garcez, A.D.A. and Russo, A. (2004). Reasoning about requirements evolution using clustered belief revision.
  63. Garcez, A.D., Gabbay, D. and Lamb, L.C. (2004). Argumentation neural networks.
  64. Garcez, A.D., Gabbay, D.M. and Lamb, L.C. (2004). Towards a Connectionist Argumentation Framework. 16th European Conference on Artificial Intelligence (ECAI'04) Valencia.
  65. Garcez, A.D. and Gabbay, D.M. (2004). Fibring Neural Networks. 19th National Conference on Artificial Intelligence (AAAI'04) San Jose, California.
  66. Garcez, A.D. and Lamb, L.C. (2004). Reasoning about Time and Knowledge in Neural-Symbolic Learning Systems. Advances in Neural Information Processing Systems 16 (NIPS 2003) Vancouver.
  67. Garcez, A.D., Dustdar, S., Gall, H., Lucia, A., Mana, A., Menzies, T. … Russo, A. (2004). Proceedings of Automated Software Engineering: Workshops at the 19th International Conference on Automated Software Engineering ASE'04.
  68. Rodrigues, O., Garcez, A.D. and Russo, A. (2003). Reasoning about Requirements Evolution using Clustered Belief Revision. ESEC/FSE International Workshop on Intelligent Technologies for Software Engineering (WITSE'03) September, Helsinki.
  69. Spanoudakis, G., Garcez, A.D. and Zisman, A. (2003). Revising Rules to Capture Requirements Traceability Relations: A Machine Learning Approach. Fifteenth International Conference on Software Engineering and Knowledge Engineering (SEKE'03) July, San Francisco.
  70. Garcez, A.D., Lamb, L.C., Broda, K. and Gabbay, M. (2003). Distributed Knowledge Representation in Neural--Symbolic Learning Systems: A Case Study. AAAI International FLAIRS Conference Florida.
  71. Spanoudakis, G., Zisman, A. and Garcez, A. (2003). Proceedings of Workshop on Intelligent Technologies for Software Engineering (WITSE03). In conjunction with the 9th European Software Engineering Conference and the 11th Symposium on Foundations of Software Engineering.
  72. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2002). A Connectionist Inductive Learning System for Modal Logic Programming. 9th IEEE International Conference on Neural Information Processing ICONIP'02 November, Singapore.
  73. Garcez, A.D. (2002). Extended Theory Refinement in Knowledge-based Neural Networks. IEEE International Joint Conference on Neural Networks (IJCNN'2002). World Congress on Computational Intelligence May, Hawaii.
  74. Garcez, A.D., Russo, A., Nuseibeh, B. and Kramer, K. (2001). An Analysis-Revision Cycle to Evolve Requirements Specifications. 16th IEEE International Conference on Automated Software Engineering (ASE-2001) November, San Diego.
  75. Broda, K., Garcez, A.D. and Gabbay, D.M. (2000). Metalevel Priorities and Neural Networks. Workshop on the Foundations of Connectionist-Symbolic Integration ECAI2000 August, Berlin.
  76. Garcez, A.D., Broda, K., Gabbay, D.M. and de Souza, A.F. (1999). Knowledge Extraction from Trained Neural Networks: A Position Paper. 6th IEEE International Conference on Neural Information Processing ICONIP'99 November, Australia.
  77. Basilio, R., Zaverucha, G. and Garcez, A.D. (1998). Inducing Relational Concepts with Neural Networks via the LINUS System. 5th International Conference on Neural Information Processing ICONIP'98 October, Kitakyushu, Japan.
  78. Garcez, A.D., Zaverucha, G. and da Silva, V.N.L. (1997). Applying the Connectionist Inductive Learning and Logic Programming System to Power Systems Diagnosis. IEEE International Joint Conference on Neural Networks (IJCNN'97) June, Houston.
  79. Garcez, A.D., Zaverucha, G. and de Carvalho, L.A.V. (1996). Logic Programming and Inductive Learning in Artificial Neural Networks. Workshop on Knowledge Representation and Neural Networks. XX German Conference on Artificial Intelligence KI96 September, Dresden, Germany.
  80. Garcez, A.D., Zaverucha, G. and de Carvalho, L.A.V. (1996). Logical Inference and Inductive Learning in Artificial Neural Networks. Workshop on Neural Networks and Structured Knowledge ECAI'96 August, Budapest.
  81. Garcez, A.D., Zaverucha, G. and da Silva, V.N.L. (1996). Programa çao em Lógica Estendida e Aprendizado Indutivo em Redes Neurais:Uma Aplicaçao em Sistemas de Potencia. 3rd Simposio Brasileiro de Redes Neurais (SBRN'96) Recife, Brasil.
  82. Garcez, A.D., Zaverucha, G. and Carvalho, L.A.V. (1995). Inferencia Lógica e Aprendizado Automáatico em Redes Neurais: Uma Representaçao Integrada do Conhecimento. 2nd Congresso Brasileiro de Redes Neurais CBRN'95 October, Curitiba, Brazil.
  83. Philps, D., Weyde, T., Garcez, A.D. and Batchelor, R. Continual Learning Augmented Investment Decisions.

Journal articles (54)

  1. Tran, S.N., Garcez, A.D., Weyde, T., Yin, J., Zhang, Q. and Karunanithi, M. (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.
  2. Reyes-Aldasoro, C.C., Ngan, K.H., Ananda, A., d’Avila Garcez, A., Appelboam, A. and Knapp, K.M. (2020). Geometric semi-automatic analysis of radiographs of Colles’ fractures. PLOS ONE, 15(9). doi:10.1371/journal.pone.0238926.
  3. Tran, S.N., Ngo, S. and Garcez, A.D. (2020). Probabilistic approaches for music similarity using restricted Boltzmann machines. Neural Computing and Applications, 32(8), pp. 3999–4008. doi:10.1007/s00521-019-04106-y.
  4. Lemos, H., Avelar, P., Prates, M., Garcez, A. and Lamb, L. (2020). Neural-Symbolic Relational Reasoning on Graph Models: Effective Link Inference and Computation from Knowledge Bases. pp. 647–659. doi:10.1007/978-3-030-61609-0_51.
  5. Lamb, L.C., d'Avila Garcez, A., Gori, M., Prates, M.O.R., Avelar, P.H.C. and Vardi, M.Y. (2020). Graph neural networks meet neural-symbolic computing: A survey and perspective. IJCAI International Joint Conference on Artificial Intelligence, 2021-January, pp. 4877–4884.
  6. Mota, E., Howe, J.M., Schramm, A. and d'Avila Garcez, A. (2019). Efficient Predicate Invention using Shared NeMuS. 14th International Workshop on Neural-Symbolic Learning and Reasoning.
  7. Garcez, A.D., Gori, M., Lamb, L.C., Serafini, L., Spranger, M. and Tran, S.N. (2019). Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. Journal of Applied Logics, 6(4), pp. 611–631.
  8. Garcez, A.D. and Besold, T.R. (2019). Editorial. Journal of Applied Logics, 6(4), pp. 609–610.
  9. Hirose, A., Micheli, A., d'Avila Garcez, A.S., Ahn, C.K., Pan, G., Karimi, H.R. … He, H. (2019). Editorial: Booming of Neural Networks and Learning Systems. IEEE Transactions on Neural Networks and Learning Systems, 30(1), pp. 2–10. doi:10.1109/tnnls.2018.2884305.
  10. Tran, S.N. and 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.
  11. Besold, T.R., Garcez, A.D., Stenning, K., van der Torre, L. and van Lambalgen, M. (2017). Reasoning in Non-probabilistic Uncertainty: Logic Programming and Neural-Symbolic Computing as Examples. Minds and Machines, 27(1), pp. 37–77. doi:10.1007/s11023-017-9428-3.
  12. Cherla, S., Tran, S.N., d’Avila Garcez, A. and Weyde, T. (2017). Generalising the Discriminative Restricted Boltzmann Machines. pp. 111–119. doi:10.1007/978-3-319-68612-7_13.
  13. Percy, C., França, M., Dragičević, S. and d’Avila Garcez, A. (2016). Predicting online gambling self-exclusion: an analysis of the performance of supervised machine learning models. International Gambling Studies, 16(2), pp. 193–210. doi:10.1080/14459795.2016.1151913.
  14. Forechi, A., De Souza, A.F., Oliveira Neto, J.D., Aguiar, E.D., Badue, C., d’Avila Garcez, A. … Oliveira-Santos, T. (2016). Fat-Fast VG-RAM WNN: A high performance approach. Neurocomputing, 183, pp. 56–69. doi:10.1016/j.neucom.2015.06.104.
  15. Guo, S., Roudsari, A. and Garcez, A.D.A. (2015). Modelling Clinical Diagnostic Errors: A System Dynamics Approach. Studies in Health Technology and Informatics, 208, pp. 160–164. doi:10.3233/978-1-61499-488-6-160.
  16. Guo, S., Roudsari, A. and Garcez, A.D.A. (2015). A System Dynamics Approach to Analyze Laboratory Test Errors. Studies in Health Technology and Informatics, 210, pp. 266–270. doi:10.3233/978-1-61499-512-8-266.
  17. Perotti, A., Boella, G. and Garcez, A.D.A. (2015). Learning and extracting tacit knowledge from processes using the Neural-Symbolic paradigm. Sistemi Intelligenti, 27(1), pp. 141–166.
  18. Besold, T.R., Kühnberger, K.-.U., Garcez, A.D., Saffiotti, A., Fischer, M.H. and Bundy, A. (2015). Anchoring Knowledge in Interaction: Towards a Harmonic Subsymbolic/Symbolic Framework and Architecture of Computational Cognition. pp. 35–45. doi:10.1007/978-3-319-21365-1_4.
  19. Perotti, A., Boella, G. and d'Avila Garcez, A. (2014). Runtime Verification Through Forward Chaining. Electronic Proceedings in Theoretical Computer Science, 169, pp. 68–81. doi:10.4204/eptcs.169.8.
  20. Ali, H., Garcez, A.S.D., Tran, S.N., Zhou, X. and Iqbal, K. (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.
  21. Besold, T.R., Garcez, A.D., Kühnberger, K.-.U. and Stewart, T.C. (2014). Neural-symbolic networks for cognitive capacities. Biologically Inspired Cognitive Architectures, 9, pp. iii–iv. doi:10.1016/s2212-683x(14)00061-9.
  22. França, M.V.M., Zaverucha, G. and D'Avila Garcez, A.S. (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.
  23. Guo, S., Roudsari, A. and Garcez, A.D.A. (2014). A Causal Loop Approach to the Study of Diagnostic Errors. Studies in Health Technology and Informatics, 205, pp. 73–77. doi:10.3233/978-1-61499-432-9-73.
  24. Tran, S.N. and Garcez, A.D. (2014). Low-Cost Representation for Restricted Boltzmann Machines. pp. 69–77. doi:10.1007/978-3-319-12637-1_9.
  25. d'Avila Garcez, A.S., Gabbay, D.M. and Lamb, L.C. (2013). A neural cognitive model of argumentation with application to legal inference and decision making. Journal of Applied Logic.
  26. De Penning, L., Garcez, A.D.A. and Meyer, J.J.C. (2013). Dreaming machines: On multimodal fusion and information retrieval using neural-symbolic cognitive agents. OpenAccess Series in Informatics, 35, pp. 89–94. doi:10.4230/OASIcs.ICCSW.2013.89.
  27. De Penning, H.L.H., Den Hollander, R.J.M., Bouma, H., Burghouts, G.J. and D'Avila Garcez, A.S. (2012). A neural-symbolic cognitive agent with a mind's eye. AAAI Workshop - Technical Report, WS-12-11, pp. 9–14.
  28. D'Avila Garcez, A., Hitzler, P. and Lamb, L.C. (2012). AAAI Workshop - Technical Report: Preface. AAAI Workshop - Technical Report, WS-12-11.
  29. Perotti, A., D'Avila Garcez, A., Boella, G. and Rispoli, D. (2012). Neural-symbolic rule-based monitoring. AAAI Workshop - Technical Report, WS-12-11, pp. 21–26.
  30. D'avila Garcez, A.S. and Zaverucha, G. (2012). Multi-instance learning using recurrent neural networks. Proceedings of the International Joint Conference on Neural Networks. doi:10.1109/IJCNN.2012.6252784.
  31. Agrawal, V., Baier, J., Bekris, K., Chen, Y., D'Avila Garcez, A.S., Hitzler, P. … Vassos, S. (2012). Reports of the AAAI 2012 conference workshops. AI Magazine, 33(4), pp. 119–127. doi:10.1609/aimag.v33i4.2444.
  32. Boella, G., Tosatto, S.C., Garcez, A.D.A., Genovese, V., Perotti, A. and Van Der Torre, L. (2012). Learning and reasoning about norms using neural-symbolic systems. 11th International Conference on Autonomous Agents and Multiagent Systems 2012, AAMAS 2012: Innovative Applications Track, 1, pp. 440–447.
  33. Borges, R.V., Garcez, A.D. and 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.
  34. De Penning, H.L.H., D'Avila Garcez, A.S., Lamb, L.C. and Meyer, J.J.C. (2011). Neural-symbolic cognitive agents: Architecture and theory. Imperial College Computing Student Workshop - Proceedings of ICCSW'11 pp. 10–16.
  35. Boella, G., Tosatto, S.C., Garcez, A.D.A., Genovese, V., Ienco, D. and Van Der Torre, L. (2011). Neural symbolic architecture for normative agents. 10th International Conference on Autonomous Agents and Multiagent Systems 2011, AAMAS 2011, 2, pp. 1135–1136.
  36. Borges, R.V., Garcez, A.D.A. and Lamb, L.C. (2010). Integrating model verification and self-adaptation. ASE'10 - Proceedings of the IEEE/ACM International Conference on Automated Software Engineering pp. 317–320. doi:10.1145/1858996.1859060.
  37. Aha, D.W., Boddy, M., Bulitko, V., Garcez, A.D., Doshi, P., Edelkamp, S. … Natarajan, S. (2010). Reports of the AAAI 2010 Conference Workshops. AI Magazine, 31(4), pp. 95–108.
  38. Stathis, K., Garcez, A.D. and Givan, R. (2009). Special Issue: Reinforcement Learning Preface. JOURNAL OF ALGORITHMS-COGNITION INFORMATICS AND LOGIC, 64(4), pp. 125–126. doi:10.1016/j.jalgor.2009.04.001.
  39. Stathis, K., d'Avila Garcez, A. and Givan, R. (2009). Preface. Journal of Algorithms, 64(4), pp. 125–126. doi:10.1016/j.jalgor.2009.04.001.
  40. Garcez, A.D. and Gabbay, D.M. (2009). Logical Modes of Attack in Argumentation Networks. Studia Logica, 93, pp. 199–230.
  41. Borges, R.V., d'Avila Garcez, A.S. and Lamb, L.C. (2008). A neural-symbolic perspective on analogy. Behavioral and Brain Sciences, 31(4), pp. 379–380. doi:10.1017/S0140525X08004482.
  42. Garcez, A.D., Borges, R.V. and Lamb, L.C. (2008). A Neural-Symbolic Perspective on Analogy. Commentary on Leech et al, Analogy as Relational Priming. Behavioral and Brain Sciences, 31(4), pp. 379–380.
  43. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2007). Connectionist Modal Logic: Representing Modalities in Neural Networks. Theoretical Computer Science, 371(1-2), pp. 34–53.
  44. Dafas, P. and Garcez, A.D. (2007). Discovering Meaningful Rules from Gene Expression Data. Current Bioinformatics, 2(3), pp. 157–168.
  45. Garcez, A.D. (2007). Abductive Reasoning in Neural-Symbolic Learning Systems. Topoi: An International Review of Philosophy. Logic and Cognition, 26, pp. 37–49.
  46. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2006). Connectionist Computations of Intuitionistic Reasoning. Theoretical Computer Science, 358(1), pp. 34–55.
  47. Garcez, A.D. and Lamb, L.C. (2006). A Connectionist Computational Model for Epistemic and Temporal Reasoning. Neural Computation, 18(7), pp. 1711–1738.
  48. Garcez, A.D., Gabbay, D.M. and Lamb, L.C. (2005). Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems. Journal of Logic and Computation, 15(6), pp. 1041–1058.
  49. Garcez, A.D., Lamb, L.C., Broda, K., Gabb, and Gabbay, D.M. (2004). Applying Connectionist Modal Logics to Distributed Knowledge Representation Problems. International Journal on Artificial Intelligence Tools, 13(1), pp. 115–139.
  50. Garcez, A.D., Gabbay, D.M., Holldobler, S. and Taylor, J.G. (2004). Journal of Applied Logic, Special Volume on Neural-Symbolic Systems. Journal of Applied Logic, Special Volume on Neural-Symbolic Systems.
  51. Garcez, A.D., Russo, A., Nuseibeh, B. and Kramer, J. (2003). Combining Abductive Reasoning and Inductive Learning to Evolve Requirements Specifications. Software IEE Proceedings, 150(1), pp. 25–38.
  52. Garcez, A.D. and Thomaz, C.E. (2003). Book Review: Neural Networks

    for Pattern Recognition (by Christopher M. Bishop).     Journal of Logic and Computation, 13(4), p. 627.
  53. Garcez, A.D., Broda, K. and Gabbay, D.M. (2001). Symbolic Knowledge Extraction from Trained Neural Networks: A Sound Approach. Artificial Intelligence, 125(1-2), pp. 153–205.
  54. Garcez, A.D. and Zaverucha, G. (1999). The Connectionist Inductive Learning and Logic Programming System. Applied Intelligence Journal, 11(1), pp. 59–77.

Reports (15)

  1. Ren, L. and Garcez, A.D. (2008). Rule Extraction from Support Vector Machines: A Geometric Approach. Technical Report. Department of Computing, City University London.
  2. Dafas, P. and Garcez, A.D. (2006). Applied Temporal Rule Mining to Time Series. Department of Computing, City University London.
  3. d'Avila Garcez, A. (2006). Proceedings of ECAI International Workshop on Neural-Symbolic Learning and Reasoning NeSy 2006..
  4. d'Avila Garcez, A. (2005). Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning NeSy 2005..
  5. Dafas, P. and d'Avila Garcez, A. (2005). Applied temporal Rule Mining to Time Series..
  6. Garcez, A.D., Gabbay, D.M. and Lamb, L.C. (2004). Argumentation Neural Networks: Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems. Department of Computing, City University London.
  7. Rodrigues, O., Garcez, A.D. and Russo, A. (2003). Reasoning about Requirements Evolution using Clustered Belief Revision. Department of Computer Science, King's College London.
  8. Garcez, A.D. and Gabbay, D.M. (2003). Fibring Neural Networks. Department of Computing, City University London.
  9. d'Avila Garcez, A., Spanoudakis, G. and Zisman, A. (2003). Proceedings of ACM ESEC/FSE International Workshop on Intelligent Technologies for Software Engineering WITSE03..
  10. Garcez, A.D., Lamb, L.C. and Gabbay, D.M. (2002). A Connectionist Inductive Learning System for Modal Logic Programming. Department of Computing, Imperial College, London.
  11. Garcez, A.D., Russo, A., Nuseibeh, B. and Kramer, J. (2002). Combining Abductive Reasoning and Inductive Learning to Evolve Requirements Specifications. Department of Computing, Imperial College, London.
  12. Garcez, A.D., Broda, K. and Gabbay, D.M. (1998). Symbolic Knowledge Extraction from Trained Neural Networks: A New Approach. Department of Computing, Imperial College, London.
  13. Garcez, A.D. (1998). Knowledge Extraction from Neural Networks, MPhil-PhD Transfer Report. Department of Computing, Imperial College, London.
  14. Garcez, A.D. (1997). Towards Neural-Symbolic Integration, PhD First Year Report. Department of Computing, Imperial College, London.
  15. Garcez, A.D. (1994). Inferencia Automática e Modelos Conexionistas. Technical Report, COPPE. Engenharia de Sistemas e Computaçao, UFRJ, Rio de Janeiro.

Theses/dissertations (3)

  1. Garcez, A.D. Nonmonotonic Theory Refinement in Artificial Neural Networks. (PhD Thesis)
  2. Garcez, A.D. Um Sistema Neural para Programaçao em Lógica com Aprendizado Indutivo. (Master's Thesis)
  3. Garcez, A.D. Redes Neurais: Fundamentos e Aplicaçoes. Final Year Project, Computing Engineering. (Undergraduate Dissertation)

Working paper

  1. Tran, S.N. and Garcez, A.D. (2013). Adaptive Feature Ranking for Unsupervised Transfer Learning.