posted by user: tarek_besold || 15184 views || tracked by 3 users: [display]

NCI @ KI 2015 : Neural-Cognitive Integration @ KI 2015


When Sep 22, 2015 - Sep 22, 2015
Where Dresden
Submission Deadline Jul 1, 2015
Notification Due Jul 27, 2015
Final Version Due Aug 10, 2015
Categories    neural-symbolic integration   knowledge representation   learning   reasoning

Call For Papers


1st Call for Papers for the Workshop on Neural-Cognitive Integration (TU Dresden, Germany, September 22, 2015)
--- collocated with ---
KI 2015, the 38th German Conference on Artificial Intelligence (TU Dresden, Germany, September 21 to 25, 2015).



The aim of the interdisciplinary workshop is to bring together recent work addressing questions related to open issues in neural-cognitive integration, i.e., research trying to bridge the gap(s) between different levels of description, explanation, representation, and computation in symbolic and sub-symbolic paradigms, and which sheds light onto canonical solutions or principled approaches occurring in the context of neural-cognitive integration.


A seamless coupling between learning and reasoning is commonly taken as basis for intelligence in humans and, in close analogy, also for the biologically-inspired (re-)creation of human-level intelligence with computational means. Still, one of the unsolved methodological core issues in AI, cognitive systems modelling, and cognitive neuroscience is the question of the integration between connectionist sub-symbolic (i.e., neural-level) and logic-based symbolic (i.e., cognitive-level) approaches to representation, computation, (mostly sub-symbolic) learning, and (mostly symbolic) reasoning.

Researchers therefore have for years been interested in the relation between sub-symbolic/neural and symbolic/cognitive modes of representation and computation: The brain has a neural structure which operates on the basis of low-level processing of perceptual signals, but cognition also exhibits the capability to perform high-level reasoning and symbol processing. Against this background, symbolic/cognitive interpretations of ANN architectures seem desirable as possible sources of an additional (bridging) level of explanation of cognitive phenomena of the human brain (assuming that suitably chosen ANN models correspond in a meaningful way to their biological counterparts).

Furthermore, so called neural-symbolic representations and computations promise the integration of several complementary properties: the interpretability, the possibilities of direct control, coding, and knowledge extraction offered by symbolic/cognitive paradigms, together with the higher degree of biological motivation, the learning capacities, robust fault-tolerant processing, and generalization capabilities to similar input known from sub-symbolic/neural models.

Recent years have seen new developments in the modelling and analysis of artificial neural networks (ANNs) and in formal methods for investigating the properties of general forms of representation and computation. As result, new and more adequate tools for relating the sub-symbolic/neural and the symbolic/cognitive levels of representation, computation, and (consequently) explanation seem to have become available, allowing to gain new perspectives on and insights into the interplay and possibilities of cross-level bridging and integration between paradigms.

Also, more theoretical and conceptual work in cognitive science and philosophy of mind and cognition has found its way into AI as exemplified, for instance, by the growing number of projects following an “embodied approach” to AI, in doing so hoping to solve or avoid, among others, the current mismatch between neural and symbolic perspectives on cognition and intelligence.


This workshop aims to gather researchers from different disciplines interested in (some of) the questions mentioned under "Topic and Motivation" and/or working on some aspect of neural-cognitive integration, either on a representational, computational, or explanatory level. The list of relevant topics includes but is clearly not limited to:
– Representations of symbolic knowledge by connectionist systems or the extraction of symbolic knowledge from connectionist systems;
– Neurally-inspired approaches to learning over symbolic representations; 
– Integration of logic and probabilities; 
– Structured and/or relational learning in neural paradigms; 
– Integrated neural-cognitive approaches;
– Logical reasoning carried out by neural networks or classification/categorization done by symbolic systems;
– Biologically or cognitively inspired systems integrating (elements of) both perspectives;
– Applications of neural-cognitive systems especially to cognition-related tasks; 
– Philosophical aspects of neural-cognitive interaction and/or integration.
In order to allow for a maximally integrative approach and an open discussion this workshop encourages researchers not only to present research papers but also position papers, and to address controversial problems, questions, or perspectives.

=== DATES ===
The current schedule is:
- Paper submission deadline: July 1, 2015
- Notification of acceptance: July 27, 2015
- Camera-ready versions due: August 10, 2015
- Workshop date: September 21 or 22, 2015


In order to accommodate for the different publishing traditions in different fields, we invite submissions of papers and extended abstracts.

Similar to the KI 2015 main conference, we invite papers which have to be in English and formatted according to the Springer LNCS style.
Papers can be submitted in one of the two following categories:
- Full technical papers (12 pages max., excluding references).
- Technical notes (6 pages max., excluding references).
For further details on the formatting and submission categories, please see the KI 2015 submission instructions ( ).

Extended abstracts:
Abstracts (which have to be in English) should have a length of 600-1000 words (plus references) in plain text or PDF, plus a short abstract of up to 120 words. Abstracts should (similar to papers) also be formatted according to the Springer LNCS style.

Submissions should be sent by the above stated deadline to Tarek R. Besold at tarek(dot)besold(at)uos(dot)de.


Accepted papers and abstracts will be published online in the ”Publication Series of the Institute of Cognitive Science“ (PICS, ISSN 1610-5389), a scientific series from the Institute of Cognitive Science, University of Osnabrück, unless the authors instruct us otherwise. 
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, Oxford University Press.


Workshop Co-Chairs
- Tarek R. Besold, Institute of Cognitive Science, University of Osnabrück, Germany
- Kai-Uwe Kühnberger, Institute of Cognitive Science, University of Osnabrück, Germany

Program Committee
- James Davidson, Google Inc., USA
- Artur D'Avila Garcez, City University London, UK
- Sascha Fink, Otto-von-Guericke University Magdeburg, Germany
- Luis Lamb, Universidade Federal do Rio Grande do Sul, Brazil
- Francesca Lisi, University of Bari "Aldo Moro", Italy
- Günther Palm, University of Ulm, Germany
- Constantin Rothkopf, Technical University Darmstadt, Germany
- Jakub Szymanik, University of Amsterdam, The Netherlands
- Carlos Zednik, Institute of Cognitive Science, University of Osnabrück, Germany
...more to come...

Related Resources

NIPS 2017   The Thirty-first Annual Conference on Neural Information Processing Systems
IJITE 2017   International Journal on Integrating Technology in Education
ICANN 2017   International Conference on Artificial Neural Networks 2017
DBKDA 2017   The Ninth International Conference on Advances in Databases, Knowledge, and Data Applications
IJCNN 2017   International Joint Conference on Neural Networks
ICLT 2017   3rd International Conference on Learning and Teaching
ICONIP 2017   International Conference on Neural Information Processing
LPNMR 2017   14th International Conference on Logic Programming and Non-monotonic Reasoning
ESANN 2017   25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
ICAISC 2017   International Conference on Artificial Intelligence and Soft Computing