AGI-17 Workshop on
Understanding Understanding
Call for Papers

Understanding Understanding

Call for Papers

Understanding Understanding will be a one-day workshop addressing recent work relevant to the question of machine understanding, aiming for a wide range of topics and methods to be presented and discussed. To explore the natural questions inherent within this concept the workshop aims to draw on the fields of AI, AGI, philosophy, cognitive science and psychology to cover a diverse set of methods, assumptions, approaches, and systems design and thinking in the field of AI and AGI.

Understanding seems central to the human ability to assess our own capacity for affecting change in particular contexts on particular tasks. Most humans not trained in mountain climbing will turn down an offer to climb Mount Everest. They also have an easy time explaining why they turn it down, and can probably cook up a rough outline for the kind of training that might make them change their mind. We call it a lack of understanding when issues central to a topic or problem are blissfully ignored by someone trying to solve it, and consider it a hopeless case when repeated attempts at explaining to them that they don't have sufficient understanding of the subject to make any important decisions about it are ignored.

Historically, the use of the term understanding in AI has mostly focused on natural language, which relates to the parsing and manipulation of linguistic tokens, and scene or image understanding, which again relates to parsing or largely semantics-free processing, with any discussion of understanding proper a rare occurrence. To the field of AGI, for which the topic of generality is central, this state of affairs would seem far from ideal. To investigate the phenomenon of understanding, compare systems with respect to their potential for understanding, and get to the crux of what understanding really is, seems important enough to give it more scrutiny.

We are interested in submissions from the fields on AGI, AI, psychology, and philosophy, which focus upon the concept of understanding, especially in relation to the goal of building machines that have the capacity to understand.

Among the questions and topics the workshop will address (but is not limited to) are the following:

  • How should we define understanding?
  • How can we test for understanding?
  • Is understanding an emergent property of intelligent systems?
  • Is understanding a central property of intelligent systems?
  • What are the typologies or gradations of understanding?
  • How can we create systems that exhibit understanding?
  • What is required in order to achieve understanding in machines?
  • Can understanding be achieved through hand-crafted architectures or must it emerge through self-organizing (constructivist) principles?
  • How can mainstream techniques be used towards the development of machines which exhibit understanding?
  • Do we need radically different approaches than those in use today to build systems with understanding?
  • Does building artificially intelligent machines with versus without understanding depend on the same underlying principles, or are these orthogonal approaches?
  • Do we need special programming languages to implement understanding in intelligent systems?
  • Is general intelligence necessary and/or sufficient to achieve understanding in an artificial system?
  • What differentiates systems that do and do not have understanding?
  • How can current state of the art methods in AGI address the need for understanding in machines?

Parties interested specifically in this workshop will be able to register for this one-day workshop without having to register for the entire AGI-17 conference.


Key Information:

August 18
Melbourne, Australia

Paper & Demo submission:

Due date:
July 10
Notification date:
July 25
Camera-ready date:
August 5
Submission system:


EGPAI 2017 Workshop
August 20
IJCAI-17 Conference
August 19-25
AGA-17 Workshop
August 19



Please use this text version of our CfP for distribution on other media.


Time Event
10:15-10:20Welcome by David Kremelberg
10:20-10:55Target talks, comments and discussion: "Understanding as Conceptualizing" by Pei Wang
10:55-11:30Target talks, comments and discussion: "Do Machines Understand? A Short Review of Understanding & Common Sense in Artificial Intelligence" by Kris Thorisson and David Kremelberg
11:30-11:50Invited talk: Tom Everitt: "AI Safety and Understanding"
1:00-1:30Special topics: Object+Situation; Moderators: Dave and Kris
1:30-2:00Special topics: Mechanism+Question-Answering; Moderators: Kris and Pei
2:00-2:30Special topics: Translation+Conversation; Moderators: Dave and Pei
2:30-3:00Special topics: Goal-Achievement+Artwork; Moderators: Dave and Kris

Submission Format

We welcome technical papers as well as overviews, demonstrations and position papers on a range of topics relating to the topic of understanding:

  • Design proposals for cognitive architectures targeting understanding
  • New programming languages relevant to understanding
  • New methods relevant to understanding
  • New architectural principles relevant to understanding
  • New theoretical insights relevant to understanding
  • Synergies between various approaches to understanding (theoretically, within AGI, etc.)
  • Machine education/learning needed to achieve understanding
  • Analysis of the potential and limitations of existing approaches

Papers should be between 2 and 12 pages and describe the authors' original work. Formatting can follow either the AGI-17 format or the IJCAI-17 format. Papers will be subjected to peer-review and can be accepted for oral presentation or poster presentation.

Proposals for Demonstrations should be accompanied with a 2-page extended abstract for inclusion in the workshop's proceedings. Examples include, but are not limited to: (interactively) demonstrating the performance of a system, (cognitive) architecture, or design methodology.

Oral presentations should be given by one of the authors during one of the Contributed Talks Sessions. Posters and demonstrations will be presented during the Poster & Demo Session at the end of the day. Accepted papers will be gathered into a volume of proceedings and published online.

Contributions should be submitted through EasyChair before the deadline on July 10th (23:59 Eastern time). Authors will be notified on July 25th of the acceptance or rejection of their submission, and are requested to submit a revised camera-ready version based on reviewers' comments by August 5th.


Dr. David Kremelberg (contact)

Icelandic Institute for Intelligent Machines

Dr. Kristinn R. Thórisson

Reykjavik University & Icelandic Institute for Intelligent Machines

Dr. Pei Wang

Temple University

Dr. Bas Steunebrink


Program Committee

Joscha BachHarvard University
Tarek Richard BesoldUniversity of Bremen
Jordi BiegerReykjavik University
Antonio ChellaUniversity of Palermo
Haris DindoYewno & University of Palermo
Helgi P. HelgasonActivity Steeam
David KremelbergIcelandic Institute for Intelligent Machines
Xiang LiTemple University
Tony LofthouseEvolving Solutions Ltd.
Laurent OrseauDeepMind
Javier SnaiderGoogle Inc.
Bas SteunebrinkNNAISENSE
Claes StrannegårdUniversity of Gothenburg
Kristinn R. ThórissonReykjavik University & Icelandic Institute for Intelligent Machines
Pei WangTemple University