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.
Jude Shavlik, Computer Sciences Department, University of Wisconsin-Madison, USA:
Twenty-Five Years of Combining Symbolic and Numeric Learning (slides (pdf))
Abstract: For nearly 25 years my research group has investigated the use of domain knowledge, expressed in some version of mathematical logic, that is refined or exploited by numeric-based learning algorithms. These include what we called knowledge-based neural networks and knowledge-based support vector machines. I will cover the key ideas of these methods, as well as the behind-the-scenes motivations that lead to them. I will also describe why we switched from using the phrase 'prior knowledge' to using 'advice.' Finally, I will cover some of our recent work on fast learning and inference for Markov Logic Networks (which can be viewed as a knowledge-based graphical model).
Jude Shavlik is Professor of Computer Sciences and of Biostatistics and Medical Informatics at the University of Wisconsin - Madison, and is a Fellow of the AAAI. He has been at Wisconsin since 1988, following the receipt of his PhD from the University of Illinois for his work on Explanation-Based Learning. His current research interests include machine learning and computational biology, with an emphasis on using rich sources of training information, such as human-provided advice. He served for three years as editor-in-chief of the AI Magazine and serves on the editorial board of about a dozen journals. He chaired the 1998 ICML, the 2003 IEEE Conference on Data Mining, and co-chaired the 2007 ILP Conference. His research has been supported by DARPA, NIH, NSF, AT&T, IBM, and NYNEX.
09:15 - 09:30 Welcome
09:30 - 10:30 Keynote talk: Twenty-Five Years of Combining Symbolic and Numeric Learning. Jude Shavlik, University of Wisconsin-Madison, USA (slides (pdf))
10:30 - 11:00 Coffee break
11:00 - 11:30 Neural-Symbolic Rule-Based Monitoring. Alan Perotti, Guido Boella, Artur d'Avila Garcez and Daniele Rispoli (pdf)
11:30 - 12:00 Efficiently merging symbolic rules into integrated rules. Jim Prentzas and Ioannis Hatzilygeroudis (pdf)
12:00 - 14:00 Lunch break
14:00 - 14:30 Vowel Recognition in Simulated Neurons. Christian Huyck (pdf)
14:30 - 15:00 Towards Bridging the Gap Between Pattern Recognition and Symbolic Representation Within Neural Networks. Tsvi Achler (pdf)
15:00 - 15:30 A Neural-Symbolic Cognitive Agent with a Mind's Eye. Leo de Penning, Richard Den Hollander, Henri Bouma, Gertjan Burghouts and Artur d'Avila Garcez (pdf)
15:30 - 16:00 Coffee break
16:00 - 16:30 Unsurpervised Learning in Hybrid Cognitive Architectures. Yury Vinokurov, Dean Wyatte, Christian Lebiere, Randall O'Reilly and Seth Herd (pdf)
16:30 - 17:00 Scalable Inverse Reinforcement Learning via Instructed Feature Construction. Tomas Singliar and Dragos Margineantu
17:00 - 18:00 Discussion: The Future of Machine Learning in Alan Turing's centenary
Click to enlarge.
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 computation 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:
Researchers and practitioners are invited to submit original papers that have not been submitted for review or published elsewhere. Submitted papers must be written in English and should not exceed 6 pages in the case of research and experience papers, and 3 pages in the case of position papers (including figures, bibliography and appendices) in AAAI-12 format. However, submissions are not anonymous. All submitted papers will be judged based on their quality, relevance, originality, significance, and soundness. Papers must be submitted via easychair in PDF format at https://www.easychair.org/conferences/?conf=nesy12.
Accepted papers and presentation abstracts will have to be presented during the workshop. The workshop will include extra time for audience discussion of the presentation allowing the group to have a better understanding of the issues, challenges and ideas being presented.
Accepted papers will be published in official workshop proceedings, which will be distributed during the workshop. Authors of the best papers will be invited to submit a revised and extended version of their papers to the Journal of Logic and Computation, Learning and Reasoning Corner.
Deadline for paper submission: April 4, 2012 extended!
Notification of paper acceptance: April 20, 2012
Camera-ready paper due: May 7, 2012
Workshop date: July 23rd, 2012
The workshop is open to anybody, please register via the AAAI registration website.
Artur d'Avila Garcez (City University London, UK)
Pascal Hitzler (Wright State University, Dayton, OH, U.S.A.)
Luis Lamb (Universidade Federal do Rio Grande do Sul, Brazil)
Sebastian Bader, University of Rostock, Germany
Rafael Borges, City University London, UK
Howard Bowman, University of Kent, UK
Claudia d'Amato, University of Bari, Italy
Marco Gori, University of Siena, Italy
Barbara Hammer, TU Clausthal, Germany
Steffen Hölldobler, TU Dresden, Germany
Ekaterina Komendantskaya, Sophia Antipolis, France
Kai-Uwe Kühnberger, University of Osnabrück, Germany
Gadi Pinkas, Center for Academic Studies, Israel
Florian Roehrbein, Albert Einstein College of Medicine, New York, U.S.A.
Jude Shavlik, University of Wisconsin-Madison, U.S.A.
General questions concerning the workshop should be addressed to Artur d'Avila Garcez at email@example.com.
Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions - it's a low traffic mailing list.