Why the Common Model of the mind needs holographic a-priori categories

Abstract The enterprise of developing a common model of the mind aims to create a foundational architecture for rational behavior in humans. Philosopher Immanuel Kant attempted something similar in 1781. The principles laid out by Kant for pursuing this goal can shed important light on the common model project. Unfortunately, Kant’s program has become hopelessly mired in philosophical hair-splitting. In this paper, we first use Kant’s approach to isolate the founding conditions of rationality in humans. His philosophy lends support to Newell’s knowledge level hypothesis, and together with it directs the common model enterprise to take knowledge, and not just memory, seriously as a component of the common model of the mind. We then map Kant’s cognitive mechanics to the operations which are used in the current models of cognitive architecture. Finally, we argue that this mapping can pave the way to develop the ontology of the knowledge level for general intelligence. We further show how they can be actualized in a memory system using high dimensional vectors to achieve specific cognitive abilities.

[1]  Tony A. Plate,et al.  Holographic reduced representations , 1995, IEEE Trans. Neural Networks.

[2]  Aryn Pyke,et al.  Dynamically structured holographic memory , 2014, BICA 2014.

[3]  Michael N Jones,et al.  Representing word meaning and order information in a composite holographic lexicon. , 2007, Psychological review.

[4]  A. Clark.  Whatever next? Predictive brains, situated agents, and the future of cognitive science. , 2013, The Behavioral and brain sciences.

[5]  John E. Laird,et al.  A Standard Model of the Mind: Toward a Common Computational Framework across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics , 2017, AI Mag..

[6]  Michiel van Lambalgen,et al.  A FORMALIZATION OF KANT’S TRANSCENDENTAL LOGIC , 2011, The Review of Symbolic Logic.

[7]  Trevor Cohen,et al.  Reasoning with vectors: A continuous model for fast robust inference , 2015, Log. J. IGPL.

[8]  R. Carnap,et al.  INTERNATIONAL ENCYCLOPEDIA OF UNIFIED SCIENCE. , 1939, Science.

[9]  Garrath Williams.  Kant's Account of Reason , 2017 .

[10]  Mirella Lapata,et al.  Vector-based Models of Semantic Composition , 2008, ACL.

[11]  W. Kintsch,et al.  High-Dimensional Semantic Space Accounts of Priming. , 2006 .

[12]  William J. Clancey.  The knowledge level reinterpreted: Modeling how systems interact , 2004, Machine Learning.

[13]  Allen Newell,et al.  The Knowledge Level , 1989, Artif. Intell..

[14]  Curt Burgess,et al.  The Dynamics of Meaning in Memory , 1998 .

[15]  Nicola Guarino,et al.  Formal ontology, conceptual analysis and knowledge representation , 1995, Int. J. Hum. Comput. Stud..