Bridging the Gap between Human and Automated Reasoning

The 11th ICCL summer school “Bridging the Gap between Human and Automated Reasoning” is a platform for knowledge transfer within the rapidly increasing research communities in the field of “Computational Logic”, i.e. logic based Artificial Intelligence, and “Human Reasoning”, i.e. Cognitive Science. We will offer introductory courses covering the fundamentals of cognitive science, logic and reasoning, courses at advanced levels, as well as applied courses and workshops dedicated to specialized topics and the state of the art. Among others, the lecturers will be Ruth Byrne, Emmanuelle-Anna Dietz Saldanha, Ulrich Furbach, Sarah Gaggl, Steffen Hölldobler und Marco Ragni. Furthermore, there will be a social program, which includes a Dresden city tour, an excursion to Pirna and to the saxon switzerland, a visit to the green vault in the Dresden Royal Palace and a gala dinner.

The summer school is supported by the German Academic Exchange Service (DAAD) and therefore, a limited number of grants for students and university employees will be available, which includes a waiver for the participation fee.

The deadline for applications is April 30, 2017.

Note that the 10. ICCL summer school has won the Dresden Congress Award in 2016.

You can find more information about the summer school here:

and register here:

WFAI 2107: Call for Papers

First Workshop on Forgetting in Artificial Intelligence

Held at KI 2017
September 25/26, 2017
Dortmund, Germany

Though forgetting is usually a nuisance in everyday life, it is an important
feature for human life. On the one hand, forgetting superfluous information
facilitates the task at hand. On the other hand, it is an integral part of
basic cognitive processes, like generalization, abstraction, and learning.
In this context, forgetting is the deliberate act to abolish unnecessary
knowledge possibly conserving knowledge on a higher level. Recently, the
term “machine unlearning” has been coined for the first beneficial use
described above. In this workshop the general topic of beneficial forgetting
shall be explored from different viewpoints.

The workshop aims to bring together researchers from AI, Machine Learning,
Cognitive Science, and other disciplines who are interested in understanding
how artificial systems can profit from forgetting and how beneficial
forgetting in humans can be influenced. Topics of interest include, but are
not limited to the following:
– Forgetting in knowledge management systems
– Agents with knowledge limitations
– Unlearning hypotheses in active or incremental learning
– Supporting humans to beneficially forget
– Cognitive models using or displaying beneficial forgetting processes

——- Paper Submission ——-

We invite papers, which have to be in English and formatted according to the
Springer LNCS style. Papers may report on new research that makes a
substantial contribution to the field, but also on research in progress.
Papers may have up to 8 pages (including references). Shorter papers are
also welcome.

Submission will be by email in electronic form as pdf only. Submissions
should be sent until June 18 to michael.siebers (at)

All papers will be subject to blind peer review based on the standard
criteria of relevance, significance of results, originality of ideas,
soundness, and quality of the presentation. All accepted papers will be
published in online proceedings, and will be presented at the conference.
At least one author of each accepted paper must register for the KI
conference and present the contribution.

——– Important Dates ——–

Paper Submissions Due: June 11, 2017
Acceptance Notification: July 24, 2017
Camera-ready Version Due: August 20, 2017
Workshop: September 25 or 26, 2017

——– Main Organizers ——–

Michael Siebers, Cognitive Systems Group, University of Bamberg
Christian Jilek, Smart Data & Knowledge Services Department, DFKI GmbH

——- Program Committee ——-

Christoph Beierle, FernUniversität in Hagen, Germany
Francesco Gallo, EURIX Group, Italy
Mark A. Greenwood, University of Sheffield, UK
José Hernandez-Orallo, Universitat Politècnica de València, Spain
Nattiya Kanhabua, Aalborg University, Denmark
Gabriele Kern-Isberner, TU Dortmund, Germany
Fernando Martinez, Universitat Politècnica de València, Spain
Heiko Maus, German Research Center for Artificial Intelligence (DFKI), Germany
Vasileios Mezaris, Centre for Research and Technology Hellas, Greece
Marco Ragni, Albert-Ludwigs-Universität Freiburg, Germany
Nele Rußwinkel, TU Berlin, Germany
Sven Schwarz, German Research Center for Artificial Intelligence (DFKI), Germany
Tobias Tempel, Universität Trier, Germany
Ingo J. Timm, Universität Trier, Germany
Maria Wolters, University of Edinburgh, UK

Groningen Spring School on Cognitive Modeling

Register by February 15 to avoid late fee!

Groningen Spring School on Cognitive Modeling
– ACT-R, Nengo, PRIMs, & Accumulator Models –

Date: April 3-7, 2017
Location: Groningen, the Netherlands
Fee: € 250 (late fee + €50 after February 15)
More information and registration:

We would like to invite you to the 2017 Groningen Spring School on Cognitive Modeling. As last year, the Spring School will cover four different modeling paradigms: ACT-R, Nengo, PRIMs, and Accumulator models. It thereby offers a unique opportunity to learn the relative strengths and weaknesses of these approaches. Each day will consist of four theory lectures, one on each paradigm. Each modeling paradigm also includes hands-on assignments. Although students are free to chose the number of lectures they attend, we recommend you to sign up for lectures on two of the modeling paradigms, and complete the tutorial units for one of the paradigms. At the end of each day there will be a plenary research talk, to show how these different approaches to modeling are applied.
The Spring School will be concluded with a keynote lecture and a conference dinner. We are excited to announce that Sander Bohte has accepted our invitation and will be the keynote speaker.

Admission is limited, so register soon!

Teachers: Jelmer Borst, Hedderik van Rijn, Katja Mehlhorn (University of Groningen)

ACT-R is a high-level cognitive theory and simulation system for developing cognitive models for tasks that vary from simple reaction time experiments to driving a car, learning algebra, and air traffic control. ACT-R can be used to develop process models of a task at a symbolic level. Participants will follow a compressed five-day version of the traditional summer school curriculum. We will also cover the connection between ACT-R and fMRI.

Teacher: Terry Stewart (University of Waterloo)

Nengo is a toolkit for converting high-level cognitive theories into low-level spiking neuron implementations. In this way, aspects of model performance such as response accuracy and reaction times emerge as a consequence of neural parameters such as the neurotransmitter time constants. It has been used to model adaptive motor control, visual attention, serial list memory, reinforcement learning, Tower of Hanoi, and fluid intelligence. Participants will learn to construct these kinds of models, starting with generic tasks like representing values and positions, and ending with full production-like systems. There will also be special emphasis on extracting various forms of data out of a model, such that it can be compared to experimental data.

Teacher: Niels Taatgen (University of Groningen)

How do people handle and prioritize multiple tasks? How can we learn something in the context of one task, and partially benefit from it in another task? The goal of PRIMs is to cross the artificial boundary that most cognitive architectures have imposed on themselves by studying single tasks. It has mechanisms to model transfer of cognitive skills, and the competition between multiple goals. In the tutorial we will look at how PRIMs can model phenomena of cognitive transfer and cognitive training, and how multiple goals compete for priority in models of distraction.

Accumulator Models
Teacher: Marieke van Vugt, Don van Ravenzwaaij (University of Groningen), & Martijn Mulder (University of Amsterdam)

Decisions can be described in terms of a process of evidence accumulation, modeled with a drift diffusion mechanism. The advantage of redescribing the behavioral data with an accumulator model is that those can be decomposed into more easily-interpretable cognitive mechanisms such as speed-accuracy trade-off or quality of attention. In this course, you will learn about the basic mechanisms of drift diffusion models and apply it to your own dataset (if you bring one). You will also see some applications of accumulator models in the context of neuroscience and individual differences.

Interdisciplinary College 2017

INTERDISCIPLINARY COLLEGE 2017: „Creativity and Intelligence in Brains and
Machines: From Individuals to Societies”

(March 10-17, 2017 @ Günne am Möhnesee, Germany)


== CHAIRS ==
Luc Steels (Universitat Pompeu Fabra, Barcelona, Spain)
Dieter Jaeger (Emory University, Atlanta, USA)
Tarek R. Besold (University of Bremen, Bremen, Germany)

The Interdisciplinary College (IK) is an annual, intense one-week spring
school which offers a dense state-of-the-art course program in neurobiology,
neural computation, cognitive science/psychology, artificial intelligence,
machine learning, robotics and philosophy. It is aimed at students,
postgraduates and researchers from academia and industry. By combining
humanities, science and technology, the IK endeavors to intensify dialogue
between the various disciplines. Participants come mainly – but not
exclusively – from European countries, lecturers from all over the world.
Courses include up-to-date introductions to the main fields of the IK, as
well as an in-depth treatment of the focus topic, which is changing from
year to year. The IK is also a unique social event. In the long evenings,
participants enjoy a very special atmosphere: minds meet, music is played,
and friends are made in the welcoming conference site at Lake Möhne.

The focus topic of the IK 2017 directs the attention to creativity and
intelligence as prototypically human characteristics and capacities,
investigating their role and importance for the individual but also for
society as a whole.
Over the last years creativity has become the focus of numerous research
projects and entire disciplines, ranging from investigations into the neural
foundations of human creativity to Computational Creativity as attempted
“computerization” of creative processes (or parts thereof). Creativity is
usually conceptualized as sharing a close connection with intelligence, for
instance in that the latter often is taken as a precondition of creativity.
But creativity also is a necessarily social phenomenon: While creativity
often starts out on an individual basis, and creative acts are ultimately
implemented by individuals, society very often enables creativity to happen
either in making creative individuals collaborate, or in emergently giving
rise to a genuinely collective creative process.
Language serves as connecting thread between the topics creativity,
intelligence, the individual, and society. Creativity and intelligence often
manifest in language, and individuals and society rely on (different forms
of) language as indispensable medium of communication.
Correspondingly, the IK 2017 will consider the mentioned topics from
different theoretical as well as applied perspectives, offering courses
clustered into four interwoven blocks:
– Creativity
– Neuroscience – From Data to Theory and Back
– Language
– The Social


The Foundation of Reality: Fundamentality, Space and Time

The Foundation of Reality: Fundamentality, Space and Time

13th – 15th March 2017

MBI Auditorium, Corpus Christi College, Oxford

Invited Speakers:

David Z. Albert (Columbia University)

Ralf Bader (University of Oxford)

Craig Callender (University of California, San Diego)

Michael Esfeld (University of Lausanne)

Richard Healey (University of Arizona)

Jenann Ismael (University of Arizona)

Jill North (Rutgers University)

Oliver Pooley (University of Oxford)

Jonathan Schaffer (Rutgers University)

Christian Wüthrich (University of Geneva)

Conference program: here
Registration: here


There will be come student bursaries available on a first come – first served basis, thanks to the generous support of the Analysis Trust.

The conference is organised by The Metaphysics of Entanglement research group based at the University of Oxford and funded by the Templeton World Charity Foundation.

Rudolf-Carnap-Lectures 2017

Conference Announcement and CALL FOR PAPERS

Rudolf-Carnap-Lectures 2017
Ruhr-Universität Bochum
June 8-10, 2017

*Prof. Frank C. Jackson (ANU):*
*Meaning, perception, and conceptual analysis*

It’s an honor and a pleasure to host Frank Jackson who is going to
present his work on meaning, perception, and the nature of mind in
Bochum, as always in the context of a Graduate workshop where several
PhD students and Postdocs will also have the chance to present their
ideas on themes from the work of Frank Jackson.

*Call for Papers for PhD students: *
In addition to Prof. Jackson’s lectures, several PhD-student or early
postdoc presentations (constraint: PhD finished 2014 or later) are
planned. The topic should be related to the main theme of the conference
in a loose sense. Papers will be selected based on a blind review process.

*Call for Papers for Postdocs:
*In addition we have room for one or two experienced postdoc
presentations: Postdocs (constraint: PhD finished 2010 or later) are
invited to submit an abstract indicating it to be a
postdoc-presentation. The topic should be related to the main topic in a
loose sense. Papers will be selected based on a blind review process.*
Therefore, we invite PhD students and postdocs to submit abstracts (max.
1000 words), making thesis and argument transparent,

Financial support: Those who are selected for a presentation will
receive a support for travelling and accomodation on the basis of
receipts with an upper limit (Germany: 150€; Rest of Europe: 250€;
Beyond Europe: 400€)

Submission deadline: *April 1st, 2017*.

An outline of the Lecture series, from Frank Jackson:

*Common-sense about meaning and perception*

You wonder if it is raining outside. One way to address this question is
to listen for the sound of rain on the roof. Another is to go outside
and look. Yet another is to ask someone who has been outside and attend
to the words that come out of their mouth. After reading Saul Kripke’s
puzzling Pierre paper, you wonder if Paris is indeed pretty and plan to
make your way to Paris and see for yourself. But how do you get to
Paris? One way is to utter certain sentences that contain the word
‘Paris’ in front of a travel agent and then do what they advise.

Are the claims in the above paragraph news? Of course not. This tells us
something important about the philosophy of perception and the
philosophy of language. Our theories of meaning and of perceptual
experience had better explain why what is said in that paragraph is full
of commonplaces. In these lectures I will defend views about meaning (in
the sense of reference) and about perceptual experience, which explain
why those commonplaces are commonplaces. I will also say something about
how this connects with conceptual analysis.

*Lecture 1. How to think about perceptual content and how this delivers

There is something very attractive about a relational account of
perceptual experience but, for reasons we will review, it cannot be
right. I will argue that a certain, independently attractive account of
perceptual content tells us what to put in its place. As we will see,
what we need to put in its place explains why perceptual experience is
such a wonderful source of information.

*Public Lecture 2. The nature of the mind: What kind of materialist
should I be?*

Debates over materialism have become complex juggling acts. We need –
somehow – to give due weight to the competing claims of the identity
theory and of functionalism, while, at the same time, saying something
sensible about the phenomenal side of psychology. In this lecture, I
steer a path through the jungle.

*Lecture 3. Conceptual analysis for explainers and predictors*

In this lecture, I argue that conceptual analysis is a natural offshoot
of the way we all – be we philosophers, economists, physicists, or … –
often seek to explain and predict what happens in our world and are able
to use words in doing this.

*Lecture 4: **Two-dimensionalism for Mooreans*

This lecture is about primary/A intensions versus secondary/C
intensions, and associated issues to do with the necessary a posteriori
and all that. The material will be presented in a way that makes it
accessible to philosophers in general, not just philosophy of language
mavens. I happen to believe that two-dimensionalism is largely
common-sense – thus the reference to (G.E.) Moore – once one bears in
mind the informational role of sentences.

Further details (including abstracts) see:

Scientific Organization:
Prof. Dr. Tobias Schlicht, Prof. Dr. Albert Newen
Institute for Philosophy II, Ruhr-Universität Bochum

Kognitive Systeme Workshop 2017

Kognitive Systeme: Mensch, Teams, Systeme und Automaten
Verstehen, Beschreiben und Gestalten Kognitiver (Technischer) Systeme

Universität der Bundeswehr München, 27.-29. März 2017

Prof. Axel Schulte, Flugmechanik & Flugführung, UniBw München
Prof. Ute Schmid, Angewandte Informatik / Kognitive Systeme, Uni Bamberg

Thematische Perspektive
Kognitive Aspekte bestimmen das Leben und Arbeiten von Menschen. Die Betrachtung dynamischer Prozesse der Mensch-Maschine-Interaktion (z.B. bei der Bedienung komplexer Systeme als Pilotin oder Fahrer), maschinell unterstützte Dialoge mit Kunden und Communities, Teamarbeit in formalisierten Kontexten als Crew oder Besatzung von Operationszentralen oder neue Arbeitsformen mit variabler Koordination und Kooperation werden zunehmend wichtiger. Zahlreiche Forschungsarbeiten widmen sich daher Fragestellungen an den Schnittstellen der Arbeitsorganisation und -psychologie, Mensch-Maschine-Systeme, Human Factors, Assistenz und Überwachung sowie Signalinterpretation und Automatisierungstechnik.

Die Beschreibung kognitiver Funktionen und Prozeduren wie Lernen, Planen und Handeln ist Gegenstand der Forschung, sowohl der Psychologie und Informatik, wie auch in der Regelungstheorie und Signalinterpretation. Wenn unterschiedliche Fachperspektiven bei ähnlichen Fragestellungen aufeinander treffen, entstehen spannende Fragen – nicht nur zu den grundlegenden Begrifflichkeiten, sondern auch zur eigenen Fachperspektive und dem Selbstverständnis von Fach und Forscher/in.

Die Ziele des 6. Interdisziplinären Workshops zu „Kognitiven Systemen“ lauten:

  • Darstellung eines Überblicks über aktuelle Forschungsarbeiten zur Modellbildung kognitiver Prozesse, Funktionen und Prozeduren
  • gemeinsames Erkennen und Verstehen der unterschiedlichen Perspektiven der Psychologie, der Ingenieurwissenschaften und der Informatik und
  • Erfahrungsaustausch zur Kooperation in interdisziplinären Teams.

Wir freuen uns auf Diskussionsbeträge aus psychologischer, signal-/datenverarbeitender wie automatisierungstechnischer Sicht, idealerweise mit Schnittstellen zu anderen hier relevanten Bereichen.

Auch in diesem Jahr konnten wir wieder namhafte Wissenschaftler als ‚Keynote‘-Sprecher/in gewinnen:

  • Elisabeth Andre, Universität Augsburg, Institut für Informatik:
    Multimodale Mensch-Roboter-Interaktion
  • Niels Taatgen, University of Groningen, Artificial Intelligence:
    How to defragment the multitasking mind

Zum Verständnis der gegenseitigen Perspektiven und zur gemeinsamen Diskussion werden in diesem Jahr von den örtlichen Veranstaltern zwei interaktive Sessions zu den folgenden Themen angeboten:

  • Der kognitive Agent – Wie soll er sich verhalten? (Prof. Dr. Axel Schulte)
  • Der kognitive Agent – Was macht ihn intelligent? (Prof. Dr. Ute Schmid)

Beitragsaufruf für Vorträge aus den Bereichen

  • Beschreibung und Beschreibungsmittel für:
    • Kognitive Prozesse und Funktionen von Menschen
    • Kooperation von Mensch(en) und Maschine/Automation
    • Teams
  • Berichte aus den Anwendungsfeldern: z.B. Mensch-Maschine-Systeme, Human Factors, Automaten, Humanoide Robotik, Technische Kognitive Systeme, Assistenz- und Überwachungssysteme.

Die Anmeldung sowie das Einreichen von Beiträgen als Kurzfassung (1-2 Seiten, Word/LaTeX Vorlagen online verfügbar) erfolgt online über Akzeptiert werden ausschließlich aktuelle Arbeiten zu den Themen des Workshops. Akzeptierte Beiträge werden in einem digitalen Tagungsband (max. 8 Manuskriptseiten) veröffentlicht. Für unveröffentlichte Originalarbeiten mit einem erheblichen Anteil neuer Ergebnisse, besteht die Möglichkeit einer Open-Access Publikation (mit ISSN Nummer) mit Peer Review Verfahren. Die Veranstaltungssprache ist Deutsch; die Unterlagen können auch in englischer Sprache eingereicht werden.

Der Aufruf zur Vortragsanmeldung richtet sich an:

  • Promovierende und fortgeschrittene Masterstudierende aus den genannten Bereichen
  • Forscherinnen und Forscher aus öffentlichen und privaten Einrichtungen sowie der Industrie
  • Entscheiderinnen und Bewerter aus Verbänden sowie staatlichen Dienststellen

Wir gestalten eine interaktive Workshop-Atmosphäre mit bis zu 50 teilnehmenden Personen. Auf Wunsch kann eine Teilnahmebescheinigung zur Anrechnung von Leistungen im Promotionsstudium erstellt werden.

Wichtige Termine
Abstract und/oder Teilnahmebekundung: 9. Dezember 2016
*** Frist zur Einreichung verlängert bis 04.01.2017 ***
Information zur Vortragsannahme: 5. Januar 2017
Einreichung der vollständigen Artikel: 3. März 2017

Teilnahme am Workshop
Der Workshop wird als non-profit Veranstaltung zum Selbstkostenpreis innerhalb der Universität angeboten. Im Teilnehmer/innenbeitrag von 100,- € (ermäßigter Beitrag für Studierende bis einschließlich Master/Diplom: 50,- €) sind folgende Kosten enthalten: elektronische Proceedings, Mittagessen & Erfrischungen während der Veranstaltung, ggf. Transfers und Teilnahme an einer Exkursion.

Die Veranstaltung findet an der Universität der Bundeswehr München statt. Details zur Anreise sowie eine Liste empfohlener Hotels werden nach der Vortragsannahme an die angemeldeten Teilnehmer/innen versandt.

Wissenschaftliche Leitung
Prof. Dr. Axel Schulte
E-Mail: axel.schulte(at)
Flugmechanik und Flugführung

Prof. Dr. Ute Schmid
E-Mail: ute.schmid(at)
Angewandte Informatik insb. Kognitive Systeme

Organisation vor Ort
M.Sc. Yannick Brand
E-Mail: y.brand(at)
Dipl.-Ing. Fabian Schmitt
E-Mail: fabian.schmitt(at)
Dipl. Psych. Michael Siebers, B.Sc.
E-Mail: michael.siebers(at)

Scientific Committee der Workshop-Reihe und Herausgeber/innen der Proceedings
Prof. Dr. phil. Friederike Eyssel Uni Bielefeld
Prof. Dr.-Ing. Stefan Kopp, Uni Bielefeld
Prof. Dr.-Ing. Axel Schule, UniBw München
Prof. Dr. Andreas Wendemuth, OvGU Magdeburg
Prof. Dr. rer.pol. Annette Kluge, Ruhr Uni Bochum
Dr. rer.soc. Meike Jipp, DLR Braunschweig
Prof. Dr.-Ing. Dirk Söffker, Uni Duisburg-Essen

Orginal Call_for_paper_KogSys2017

6th EVOMUSART conference


NEWS: For the 20th year anniversary of the evo* conferences a website was made available with all the information on the evoMUSART papers since 2003. Feel free to browse and bookmark:

The 6th International Conference on Computational Intelligence in Music, Sound, Art and Design (evoMUSART) will be held in Amsterdam in 19-21 April 2017, as part of the evo* event. The main goal of EvoMusArt is to bring together researchers who are using Computational Intelligence techniques for artistic tasks such as visual art, music, architecture, video, digital games, poetry, or design. The conference gives researchers in the field the opportunity to promote, present and discuss ongoing work in the area.

Important dates:
Submission: 15 November 2016
Notification to authors: 9 January 2017
Camera-ready deadline: 25 January 2017
Evo*: 19-21 April 2017

We welcome submissions which use Computational Intelligence techniques (e.g. Evolutionary Computation, Artificial Life, Machine Learning, Swarm Intelligence) in the generation, analysis and interpretation of art, music, design, architecture and other artistic fields. Submissions must be at most 16 pages long, in Springer LNCS format (instructions downloadable from Each submission must be anonymised for a double-blind review process and submitted to . The deadline for submission is 1 November 2016, and acceptance notification on 9 January 2017. Accepted papers will be presented orally or as posters at the event and included in the evoMUSART proceedings published by Springer Verlag in a dedicated volume of the Lecture Notes in Computer Science series.

Indicative topics include but are not limited to:

* Systems that create drawings, images, animations, sculptures, poetry, text, designs, webpages, buildings, etc.;
* Systems that create musical pieces, sounds, instruments, voices, sound effects, sound analysis, etc…;
* Systems that create artifacts such as game content, architecture, furniture, based on aesthetic and functional criteria;
* Systems that resort to computational intelligence to perform the analysis of image, music, sound, sculpture, or some other types of artistic object;
* Systems in which computational intelligence is used to promote the creativity of a human user;
* Theories or models of computational aesthetics;
* Computational models of emotional response, surprise, novelty;
* Representation techniques for images, videos, music, etc;
* Surveys of the current state-of-the-art in the area;
* New ways of integrating the user in the process (e.g. improvisation, co-creation, participation).

More information on the submission process and the topics of evoMUSART 2017 can be found at

We look forward to seeing you in Amsterdam in 2017!

Aspects of Neuroscience Workshops

The 6th annual International Conference “Aspects of Neuroscience” is approaching. This year apart from 6 keynote lectures given by outstanding neuroscientists we organize Friday Workshop Session. If you would like to improve your soft skills or learn new methods, do not miss the opportunity!

More information about the Workshops on our website:

Only registered participants can take part in workshops. Check out the whole Programme of Aspects of Neuroscience and register for our event.

Abstract submission deadline: 1st November 2016
Passive registration deadline: 10th November 2016

Cognitive Computation @ NIPS 2016

Cognitive Computation:
Integrating Neural and Symbolic Approaches (CoCo @ NIPS 2016)
Workshop at NIPS 2016, Barcelona, Spain
December 09, 2016


The submission deadline for CoCo @ NIPS 2016 has been extended to Friday, October 14, 2016!



Barbara Hammer, Bielefed University
Pascal Hitzler, Wright State University
Risto Miikkulainen, University of Texas at Austin & Sentient Technologies, Inc.
Dan Roth, University of Illinois at Urbana-Champaign
Kristina Toutanova, Microsoft Research


Yoshua Bengio, University of Montreal
Marco Gori, University of Siena
Alessio Lomuscio, Imperial College London
Gary Marcus, New York University & Geometric Intelligence, Inc.


While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the integration of learning and reasoning in dynamic knowledge-bases, and reuse of knowledge learned in one application domain in analogous domains.

The workshop brings together established leaders and promising young scientists in the fields of neural computation, logic and artificial intelligence, knowledge representation, natural language understanding, machine learning, cognitive science and computational neuroscience. Invited lectures by senior researchers will be complemented with presentations based on contributed papers reporting recent work (following an open call for papers) and a poster session, giving ample opportunity for participants to interact and discuss the complementary perspectives and emerging approaches.

The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely translations between connectionist models and symbolic knowledge representation and reasoning for the purpose of achieving an effective integration of neural learning and cognitive reasoning, called neural-symbolic computing. The study of neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing.


The following list gives some (but by far not all) relevant keywords for the CoCo @ NIPS 2016 workshop:

– neural-symbolic computing;
– language processing and reasoning;
– cognitive agents;
– multimodal learning;
– deep networks;
– knowledge extraction;
– symbol manipulation;
– variable binding;
– memory-based networks;
– dynamic knowledge-bases;
– integration of learning and reasoning;
– explainable AI.


We invite submission of papers dealing with topics related to the research questions discussed in the workshop. The reported work can range from theoretical/foundational research to reports on applications and/or implemented systems.

We explicitly also encourage the submission of more controversial papers which can serve as basis for open discussions during the event.

Possible topics of interest include but are (by far!) 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;
– Integrated neural-symbolic reasoning;
– Neural-symbolic cognitive models;
– Biologically-inspired neural-symbolic integration;
– Applications in robotics, simulation, fraud prevention, natural language processing, semantic web, software engineering, fault diagnosis, bioinformatics, visual intelligence, etc.
– Approaches/techniques making AI and/or Machine Learning systems/algorithms better explainable or increasing human comprehensibility.

Submission instructions

– Submissions have to be made via EasyChair ( before the paper submission deadline indicated below.
– Submissions are limited to at most eight pages, an additional ninth page containing only cited references is allowed. Still, also shorter papers are expressly welcomed.
– Submissions have to use the NIPS 2016 submission format (see
– Reviewing will be single-blind, i.e., you are free to indicate your name etc. on the paper. (Still, this is not an obligation.)
Please note that at least one author of each accepted paper must register for the event and be available to present the paper at the workshop.


Accepted papers will be published in official workshop proceedings submitted to

Authors of selected papers will be invited to submit a revised and extended version of their papers to a journal special issue after the workshop.


– Deadline for paper submission (EXTENDED): October 14, 2016
– Notification of paper acceptance: October 30, 2016
– Camera-ready paper due: November 14, 2016
– Workshop date: December 09 or 10, 2016
– NIPS 2015 main conference: December 5-8, 2016


The workshop is open to anybody, please register via NIPS 2016 (


– Tarek R. Besold (University of Bremen, Germany)
– Antoine Bordes (Facebook AI Research, USA)
– Artur d’Avila Garcez (City University London, UK)
– Greg Wayne (Google DeepMind, UK)


– General questions concerning the workshop should be addressed to Tarek R. Besold at Tarek(dot)Besold(at)uni(hyphen)bremen(dot)de.
– This workshop is conceptually related to the series of International Workshops on Neural-Symbolic Learning and Reasoning (NeSy). If interested, have a look at
– Please also feel free to join the neural-symbolic integration mailing list for announcements and discussions – it’s a low traffic mailing list. If interested, register at