The Second Annual Conference on Advances in Cognitive Systems, took place in Baltimore, MD, on December 12, 13, and 14, 2013. This meeting brought together researchers with interests in human-level intelligence, complex cognition, integrated intelligent systems, cognitive architectures, and related topics. The purpose was to provide a venue for research on the initial goals of artificial intelligence and cognitive science, which aimed to explain the mind in computational terms and to reproduce the entire range of human cognitive abilities in computational artifacts. Because many researchers remain committed to this original vision, there is need for a meeting that provides a place to present recent results and pose new challenges for the field.
The conference welcomes work on any topic related to the representation or organization of complex mental structures, their use in multi-step cognition, or their acquisition from experience or instruction. Some functional capabilities that arise in this context include:
Some research communities already address such issues, including those dealing with cognitive architectures, cognitive robotics, commonsense reasoning, qualitative modeling, and many others. We especially encourage participation from those working in these and other areas who are interested in complex cognition, human-level intelligence, and related topics.
Submissions should be either short (at most eight pages) or long (at most 16 pages). Short papers accepted for presentation at the meeting will appear in a separate conference proceedings. Long papers accepted for presentation may either be included in the proceedings or be invited to appear in the journal, Advances in Cognitive Systems, depending on the program chairs' decision.
The submission site is now open.
Papers should be formatted according to the instructions provided at
which provides Latex and Word templates. In addition, each submission should state explicitly the problem or capability it addresses, describe its response to this problem, make claims about this approach, and provide evidence in support of these claims. Every paper should also discuss related efforts, examine limitations of the reported work, and outline plans for future research.
Because the conference aims to encourage research toward a broader understanding of intelligence, its criteria for determining contributions will differ from those used in traditional circles. Progress may take many forms, including demonstrating new functionality, integrating different facets of intelligence, presenting a novel approach to an established problem, explaining complex cognition in humans, and formally analyzing a difficult new task. We also welcome submissions on new problems or testbeds that challenge existing approaches. Papers that report incremental variants of existing methods, minor improvements on performance metrics for established tasks, or mathematical analyses of component algorithms are not in themselves relevant to this meeting unless they directly aid progress toward cognitive systems with broad functionality.
Each submission will be assigned to multiple referees who will evaluate the paper for its contribution to understanding cognitive systems, clarity of claims about this contribution, convincing evidence in support of those claims, and cogent presentation of its ideas to readers. We encourage authors to examine the review form before drafting their manuscripts to ensure that their submissions address all of the dimensions on which reviewers will evaluate them.
Accepted short papers will appear in the proceedings and be selected for either oral or poster presentation at the conference. Long papers accepted for presentation may either be included in the proceedings or be invited to appear in the journal, depending on the program chairs' decision.
The conference aims to be as inclusive as possible while still fostering innovative research on the computational nature of intelligence. The conference FAQ page attempts to clarify the scope of the event. Authors who have questions about whether their research is appropriate for the meeting should contact the Program Chairs, Matthew Klenk (klenk@parc.com) and John Laird (laird@umich.edu), for additional information.
