NeSy'18
Thirteenth International Workshop on
Neural-Symbolic Learning and Reasoning

Previous events in the series:
NeSy'05 took place at IJCAI-05, Edinburgh, Scotland, 1st of August 2005.
NeSy'06 took place at ECAI2006, Riva del Garda, Italy, 29th of August 2006.
NeSy'07 took place at IJCAI-07, Hydarabad, India, 8th of January 2007.
NeSy'08 took place at ECAI2008, Patras, Greece, 21st of July 2008.
NeSy'09 took place at IJCAI-09, Pasadena, California, 11th of July 2009.
NeSy'10 took place at AAAI-10, Atlanta, Georgia, 11th of July 2010.
NeSy'11 took place at IJCAI-11, Barcelona, Catalonia (Spain), 17th of July 2011.
NeSy'12 took place at AAAI-12, Toronto, Ontaria, Canada, 23rd of July 2012.
NeSy'13 took place at IJCAI-13, Beijing, China, 5th of August 2013.
NeSy'15 took place at IJCAI-15, Buenos Aires, Argentina, 27th of July 2015.
NeSy'16 took place at HLAI 2016, New York City, New York, 16th and 17th of July 2016.
NeSy'17 took place at City, University of London, London, UK, 17th and 18th of July 2017.

Workshop Programme Available

The programme overview of NeSy'18 has become available -- please scroll down.

Keynotes & Invited Talks

Workshop Schedule

Thursday, August 23, 2018: NeSy'18 Day 1/HLAI 2018 Day 2

• 09:00 - 10:00 HLAI 2018 Keynote Paul Smolensky (John Hopkins University & Microsoft Research, USA)
• Session I:
• 10:15 - 10:20 Opening remarks
• 10:20 - 10:55 "Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning" (A. d'Avila Garcez, M. Gori, L. Lamb, L. Serafini, M. Spranger, S. Tran)
• 10:55 - 11:30 "High-Order Networks that Learn to Satisfy Logic Constraints" (G. Pinkas, S. Cohen)
• === 11:30 - 11:45 Coffee break ===
• Session II:
• 11:45 - 12:40 NeSy'18 Keynote Luciano Serafini: "An overview of Logic Tensor Networks" (Fondazione Bruno Kessler, Italy)
• === 12:40 - 14:00 Lunch break ===
• 14:00 - 15:00 HLAI 2018 Keynote Dileep George (Vicarious, USA)
• Session III:
• 15:00 - 15:35 "Semi-Supervised Learning using Differentiable Reasoning" (E. van Krieken, E. Acar, F. van Harmelen)
• 15:35 - 16:10 "Towards logics for neural conceptors" (T. Mossakowski, R. Diaconescu, M. Glauer)
• 16:10 - 16:45 "Compositionality for Recursive Neural Networks" (M. Lewis)
• === 16:45 - 17:00 Coffee Break ===
• Session IV:
• 17:00 - 17:30 "Learning with Symbols" (A. Galila, D. Silver)
• 17:30 - 18:30 NeSy'18 Keynote Hava Siegelmann (UMass Amherst & DARPA, USA)

Friday, August 24, 2018: NeSy'18 Day 2/HLAI 2018 Day 3

• Session V:
• 09:30 - 10:25 NeSy'18 Keynote Thomas Lukasiewicz: "Learning and Reasoning in Artificial Intelligence" (University of Oxford, UK)
• 10:25 - 11:00 "Revisiting direct neuralisation of first-order logic" (I. Gunn, D. Windridge)
• === 11:00 - 11:15 Coffee Break ===
• Session VI:
• 11:15 - 11:50 "Modelling Identity Rules with Neural Networks" (T. Weyde, R. Kopparti)
• 11:50 - 12:25 "Learning Representation of Relational Dynamics with Delays and Refining with Prior Knowledge" (Y. Phua, T. Ribeiro, K. Inoue)
• === 12:25 - 13:30 Lunch break ===
• 13:30 - 14:30 HLAI 2018 Keynote Hava Siegelmann: "Lifelong Learning, Abstracting and Acting" (UMass Amherst & DARPA, USA)
• Session VII:
• 14:45 - 15:20 "Position Paper: Reasoning upon Learning -- A Generic Neural-Symbolic Approach" (M. Alirezaie)
• 15:20 - 16:15 NeSy'18 Keynote Simo Dragicevic: "The Importance of Explainability in Building and Deploying Effective Supervised Learning Risk Models" (BetBuddy, UK)
• 16:15 - 16:20 Closing remarks
• 16:25 - 16:45 AGI 2018 talk "Unsupervised Language Learning in OpenCog" (A. Kolonin, A. Suarez, A. Glushchenko, B. Goertzel, C. Castillo, L. Vepstas, M. Leung, O. Baskov)
• === 16:45 - 17:00 Coffee Break ===
• 17:00 - 18:00 HLAI 2018 Keynote Vladimir G. Red'ko (Russian Academy of Sciences, Russia)

Registration

The registration for NeSy'18 has become available from the the main website of HLAI 2018: Follow this link to the registration page.

Workshop Location

NeSy'18 is hosted at the main site of HLAI 2018 in Prague, CZ. Please see the main website of HLAI 2018 for further information.

Call for Papers (Closed)

Artificial Intelligence researchers continue to face huge challenges in their quest to develop truly intelligent systems. The recent developments in the field of neural-symbolic integration bring an opportunity to integrate well-founded symbolic artificial intelligence with robust neural computing machinery to help tackle some of these challenges.

The Workshop on Neural-Symbolic Learning and Reasoning is intended to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration.

Topics of interest include but are not limited to:

• The representation of symbolic knowledge by deep networks and connectionist systems in general;
• Semi-supervised and relational learning in neural networks;
• Reasoning and logical inference using recurrent networks;
• Distilling and knowledge extraction from neural networks;
• Integrated and hybrid neuro-symbolic AI approaches;
• Integration of logic and probabilities in neural networks;
• Knowledge-based transfer learning using neural networks;
• Verification of neural networks and reasoning about time;
• Deep symbolic reinforcement learning and planning;
• Biologically-inspired neural-symbolic architectures;
• Neural-symbolic cognitive models and systems;
• Applications in robotics, simulation, fraud prevention, language processing, semantic web, software engineering, fault diagnosis, bioinformatics, visual intelligence, etc.

Important Dates

Deadline for full paper submission (CLOSED): June 18, 2018
Notification of acceptance/rejection (full papers): July 5, 2018
Deadline for late breaking paper submission (CLOSED): August 1, 2018
Notification of acceptance/rejection (late breaking papers): on continuous basis, latest by August 8, 2018
Workshop dates: August 23-24, 2018

Admission

The workshop is open to anybody, registration is available via the main website of HLAI 2018: Follow this link to the registration website.

Workshop Organisers

Tarek R. Besold (City, University of London, UK)
Artur d'Avila Garcez (City, University of London, UK)

Programme Committee

• Derek Doran, Wright State University, USA
• Richard Evans, DeepMind, UK
• Steffen Hoelldobler, TU Dresden, Germany
• Kristian Kersting, TU Darmstadt, Germany
• Luis Lamb, Universidade Federal do Rio Grande do Sul, Brazil
• Edjard Mota, Federal University of Amazonas, Brazil
• Steven Schockaert, Cardiff University, UK
• Luciano Serafini, Fondazione Bruno Kessler, Italy
• Daniel L. Silver, Acadia University, Canada
• Michael Spranger, SONY CSL, Japan
• Frank van der Velde, University of Twente, The Netherlands
• Frank van Harmelen, VU Amsterdam, The Netherlands
• Michael Witbrock, IBM Research AI, USA

Additional Information

General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek-R.Besold@city.ac.uk.
Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions - it's a low traffic mailing list.
Finally, you might want to have a look at other resources and information related to neural-symbolic integration collected on www.neural-symbolic.org.