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.
Simo Dragicevic, CEO, BetBuddy Ltd. (moderator) John McNamara, Senior Inventor, IBM James Davidson, Software Engineer, Google Brain Jamie Woodhouse, Managing Director and Head of Financial Services Management Consulting and Finance and Risk, Accenture Lonnie Hamm, Head of Data Science, Kindred Group Plc Amir Saffari, Director of Applied AI, BenevolentAI
For the first time, the 2017 edition of NeSy will feature an industry track on the second day of the workshop, July 18, 2017.
The track will cover industry applications of neural-symbolic methods (including knowledge extraction from statistical data, neural-symbolic methods integrating data and knowledge for the semantic web, etc.), with the program featuring contributions from industry and academia alike.
Also, there will be time to mix and mingle, exchange experiences from practitioners on both sides, and develop joint ideas and projects for the future.
So if you are on the job dealing with problems requiring the combination of sub-symbolic data and high-level knowledge, come and join us at City, University of London for NeSy'17!
09:30 - 10:00 "Inductive Learning in Shared Neural Multi-Spaces" (Edjard de Souza Mota, Jacob M. Howe, Artur S. d'Avila Garcez)
10:00 - 10:15 "Learning about Actions and Events in Shared NeMuS" (Milena Rodrigues Tenorio, Edjard de Souza Mota, Jacob M. Howe, Artur S. d'Avila Garcez)
10:15 - 10:30 "Category-based Inductive Learning in Shared NeMuS (Ana Carolina Melik Schramm, Edjard de Souza Mota, Jacob M. Howe, Artur S. d'Avila Garcez)
=== 10:30 - 11:00 Coffee break ===
Session II - chair: Isaac Noble
11:00 - 11:30 "Classical Planning in Deep Latent Space: From Unlabeled Images to PDDL (and back)" (Masataro Asai, Alax Fukunaga)
11:30 - 12:15 Invitd talk Alex Graves (Google DeepMind, UK)
10:15 - 10:30 "A Comparison between Deep-Q-Networks and Deep Symbolic Reinforcement Learning" (Aimore R. R. Dutra, Artur S. d'Avila Garcez)
=== 10:30 - 11:00 Coffee break ===
Session VI - chair: Tarek R. Besold
11:00 - 11:30 "Propositional Rule Extraction from Neural Networks under Background Knowledge" (Maryam Labaf, Pascal Hitzler, Anthony B. Evans)
11:30 - 12:00 "Explaining Trained Neural Networks with Semantic Web Technologies: First Steps" (Md Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael Raymer, Pascal Hitzler)
12:00 - 12:15 "Confidence Values and Compact Rule Extraction From Probabilistic Neural Networks" (Simon Odense, Artur S. d'Avila Garcez)
=== 12:15 - 14:00 Lunch break ===
Session VII - chair: Simo Dragicevic
14:00 - 14:45 Invited talk Chris Percy (BetBuddy Ltd., UK)
=== 14:45 - 15:15 Coffee Break ===
15:15 - 16:45 Industry Panel Discussion: Explainable AI, Simo Dragicevic (moderator), John McNamara, James Davidson, Jamie Woodhouse, Lonnie Hamm, Amir Saffari
16:45 - 17:00 Wrap-Up
Call for Papers
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 connectionist systems;
Neural Learning theory;
Integration of logic and probabilities, e.g., in neural networks, but also more generally;
Structured learning and relational learning in neural networks;
Logical reasoning carried out by neural networks;
Integrated neural-symbolic approaches;
Extraction of symbolic knowledge from trained neural networks;
Applications in robotics, simulation, fraud prevention, natural language processing, semantic web,
software engineering, fault diagnosis, bioinformatics, visual intelligence, etc.
Publication
Accepted papers and abstracts will be published in official workshop proceedings within the CEUR-WS.org series.
Accepted abstracts will also be included in the official workshop proceedings.
Important Dates
Deadline for paper submission (EXTENDED): May 24, 2017 Notification of paper acceptance/rejection: June 14, 2017 Deadline for abstract submission: June 18, 2017 Notification of abstract acceptance/rejection: June 25, 2017 Camera-ready paper due: July 2, 2017 Workshop date: July 17-18, 2017
The main campus of City, University of London, is located at Northampton Square in central London. There are many hotels and accommodation options nearby, among them the following:
Local Chair at City, University of London: Simon Odense On-Site Organisation Support: Yihan Wu (University of Minnesota, U.S.A.)
Programme Committee
Raquel Alhama, University of Amsterdam
James Davidson, Google Brain
Richard Evans, Google DeepMind
Barbara Hammer, Bielefeld University
Thomas Icard, Stanford University
Kai-Uwe Kuehnberger, University of Osnabrueck
Luis Lamb, Universidade Federal do Rio Grande do Sul
Thomas Lukasiewicz, University of Oxford
Edjard Mota, Federal University of Amazonas
Terrence C. Stewart, University of Waterloo
Serge Thill, University of Skoevde
Son Tran, CSIRO Australia
Stefan Wermter, University of Hamburg
Additional Information
General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek.Besold@uni-bremen.de.
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.
