Department of Computing

Artur d'Avila Garcez

Reader

Photo of Dr Artur d'Avila Garcez Dr Artur d'Avila Garcez
Reader
Room: A309
Department of Computing
School of Informatics
City University
London EC1V OHB

aag@soi.city.ac.uk
tel: +44 20 7040 8344
fax: +44 20 7040 0244

The Machine Learning group webpage

Neural-Symbolic Learning and Reasoning, Dagstuhl Seminar 14381, Dagstuhl, Germany, September 14-19, 2014 (organiser).

23rd International Joint Conference on Artificial Intelligence (IJCAI'13), Beijing, August 2013 (Senior Programme Committee).

9th Workshop on Neural-Symbolic Learning and Reasoning (NeSy13) at IJCAI'13, Beijing, August 2013 (organiser).

Artur Garcez is a Reader in Neural-Symbolic Computation at the School of Informatics, City University London. He holds a Ph.D. in Computer Science (2000) from Imperial College London. He is a Fellow of the British Computer Society (FBCS).

Currently processing:

  1. S. Tran and A. S. d'Avila Garcez. Logic Extraction from Deep Belief Networks. In ICML Workshop on Representation Learning, Edinburgh, Scotland, July 2012.

  2. A. Perotti, G. Boella, A. d'Avila Garcez and D. Rispoli. Neural-Symbolic Rule-Based Monitoring. In AAAI Workshop on Neural-Symbolic Learning and Reasoning NeSy12, Toronto, Canada, July 2012.

  3. L. de Penning, R. den Hollander, H. Bouma, G. Burghouts and A. S. d'Avila Garcez. A Neural-Symbolic Cognitive Agent with a Minds Eye. In AAAI Workshop on Neural-Symbolic Learning and Reasoning NeSy12, Toronto, Canada, July 2012.

  4. A. S. d'Avila Garcez and G. Zaverucha. Multi-instance Learning using Recurrent Neural Networks. In Proc. IJCNN 2012, Brisbane, Australia, June 2012.

  5. G. Boella, S. Colombo-Tosatto, A. S. d'Avila Garcez, V. Genovese, A. Perotti and L. van der Torre. Learning and Reasoning about Norms using Neural-Symbolic Systems. In Proc. AAMAS 2012, Valencia, Spain, June 2012.

  6. L. de Penning, A. S. d'Avila Garcez, L. C. Lamb and J. J. Meyer. Online Spatiotemporal Learning and Reasoning: Achieving Effective Adaptation in Driving Assessment and Visual Intelligence (submitted).

  7. M. Franca, G. Zaverucha and A. S. d'Avila Garcez. Fast Relational Learning using Bottom Clauses in Artificial Neural Networks. In Proc. ILP 2012, Dubrovnik, LNCS, Sep 2012.

Garcez has an established track record of research in Neural Computing, Artificial Intelligence and Computer Science Logic. He has co-authored two books: Neural-Symbolic Cognitive Reasoning, with Lamb and Gabbay (Springer 2009), and Neural-Symbolic Learning Systems, with Broda and Gabbay (Springer 2002). His research has led to publications in Behavioral & Brain Sciences, Theoretical Computer Science, Neural Computation, Journal of Logic and Computation, Artificial Intelligence and Studia Logica. He has consistently published at the flagship Artificial Intelligence and Neural Computation conferences AAAI, NIPS, IJCAI, IJCNN, ECAI.

Garcez is editor-in-chief of the Neural Computing and Artificial Intelligence book series. He is area scientific editor of the Journal of Applied Logic (Logics and Neural Networks), area editor of the Journal of Logic and Computation (Reasoning and Learning, with L. Valiant), associate editor of the International Journal on Artificial Intelligence Tools, and member of the editorial boards of The Logic Journal of the IGPL and The International Journal of Hybrid Intelligent Systems. Garcez is a member of the advisory board of the Cognitive Technologies book series. He is Associate Member of Behavioral and Brain Sciences and a founding co-chair of the International Workshop on Neural-Symbolic Learning and Reasoning (NeSy), held yearly at IJCAI, ECAI or AAAI since 2005.

Garcez has acted as reviewer for a number of international journals on Logic, Cognitive Science, Neural Computation and Artificial Intelligence, including IEEE Transactions on Neural Networks, Artificial Intelligence, Machine Learning, Cognitive Systems Research, AI Communications, Cognitive Science, Neurocomputing, Information and Computation. He has guest-edited two journal special issues, and co-edited two research monographs. He has served on the Programme Committee or Organizing Committee of a large number of international conferences and workshops, including IJCAI, NIPS, AAAI, ECAI, ICANN, ASE and IJCNN.

Garcez was awarded a two-year Nuffield foundation research grant in the area of neural-symbolic integration (2002-2004). He was Principal Investigator at City University on the EU-funded research project BioGrid (2003-2004) and industry-funded projects RoboCup Physical Visualization League (2007) and Dynamic Fraud Prevention (2009). He was co-investigator on the EU-funded research project Genestream (2003), was awarded a Daiwa Foundation Grant (2006), and has been consistently awarded conference travel grants by The Royal Society (2002, 2003, 2004, 2005, 2007, 2010).

Selected Publications (complete list available here; google scholar profile here):

  1. R. V. Borges, A. S. d'Avila Garcez and L. C. Lamb. Learning and Representing Temporal Knowledge in Recurrent Networks. IEEE Transactions on Neural Networks, 22(12):2409 - 2421, December 2011.

  2. L. de Penning, A. S. d'Avila Garcez, L. C. Lamb and J. J. Meyer. A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning. In Proc. 22nd International Joint Conference on Artificial Intelligence, IJCAI'11, Barcelona, Spain, July 2011.

  3. Artur S. d'Avila Garcez, L. C. Lamb and D. M. Gabbay. Neural-Symbolic Cognitive Reasoning. Cognitive Technologies, Springer, ISBN 978-3-540-73245-7, 2009.

  4. Artur S. d'Avila Garcez, D. M. Gabbay, O. Ray and J. Woods. Abductive Reasoning in Neural-Symbolic Learning Systems. Topoi: An International Review of Philosophy, 26:37-49, March 2007.

  5. Artur S. d'Avila Garcez, L. C. Lamb and D. M. Gabbay. Connectionist Modal Logic: Representing Modalities in Neural Networks. Theoretical Computer Science, 371(1-2):34-53, February 2007.

  6. Artur S. d'Avila Garcez, L. C. Lamb and D. M. Gabbay. Connectionist Computations of Intuitionistic Reasoning. Theoretical Computer Science, 358(1):34-55, July 2006.

  7. Artur S. d'Avila Garcez and L. C. Lamb. A Connectionist Computational Model for Epistemic and Temporal Reasoning. Neural Computation, 18(7):1711-1738, July 2006.

  8. Artur S. d'Avila Garcez, D. M. Gabbay and L. C. Lamb. Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems. Journal of Logic and Computation 15(6):1041-1058, December 2005.

  9. Artur S. d'Avila Garcez, K. Broda and D. M. Gabbay. Neural-Symbolic Learning Systems: Foundations and Applications, Perspectives in Neural Computing, Springer, ISBN 1-85233-512-2, 2002.

  10. Artur S. d'Avila Garcez, K. Broda and D. M. Gabbay. Symbolic Knowledge Extraction from Trained Neural Networks: A Sound Approach. Artificial Intelligence, 125(1-2):153-205, January 2001.

Office Hours: Mondays, 16:00 - 18:00 (Term 1, 2012/13)