The Role of Logic in AGI Systems: Towards a Lingua Franca for General Intelligence

Systems for general intelligence require a significant potential to model a variety of different cognitive abilities. It is often claimed that logic-based systems ‐ although rather successful for modeling specialized tasks ‐ lack the ability to be useful as a universal modeling framework due to the fact that particular logics can often be used only for special purposes (and do not cover the whole breadth of reasoning abilities) and show significant weaknesses for tasks like learning, pattern matching, or controlling behavior. This paper argues against this thesis by exemplifying that logic-based frameworks can be used to integrate different reasoning types and can function as a coding scheme for the integration of symbolic and subsymbolic approaches. In particular, AGI systems can be based on logic frameworks.

[1]  Pascal Hitzler,et al.  Connectionist model generation: A first-order approach , 2008, Neurocomputing.

[2]  Pei Wang,et al.  Rigid Flexibility: The Logic of Intelligence , 2006 .

[3]  Angela Schwering,et al.  Restricted Higher-Order Anti-Unification for Analogy Making , 2007, Australian Conference on Artificial Intelligence.

[4]  Robert W. Hasker.  The replay of program derivations , 1995 .

[5]  D. Gentner,et al.  The analogical mind : perspectives from cognitive science , 2001 .

[6]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[7]  Brian Falkenhainer,et al.  The Structure-Mapping Engine: Algorithm and Examples , 1989, Artif. Intell..

[8]  Marvin Minsky,et al.  A framework for representing knowledge" in the psychology of computer vision , 1975 .

[9]  John E. Hummel,et al.  Distributed representations of structure: A theory of analogical access and mapping. , 1997 .

[10]  J. McCarthy.  Situations, Actions, and Causal Laws , 1963 .

[11]  Angela Schwering,et al.  Re-representation in a Logic-Based Model for Analogy Making , 2008, Australasian Conference on Artificial Intelligence.

[12]  Krysia Broda,et al.  Neural-symbolic learning systems - foundations and applications , 2012, Perspectives in neural computing.

[13]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[14]  K. Holyoak,et al.  The analogical mind. , 1997, The American psychologist.

[15]  Steffen Hölldobler,et al.  Ein massiv paralleles Modell für die Logikprogrammierung , 1994, WLP.

[16]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[17]  John A. Barnden.  Neural-Net Implementation of Complex Symbol-Processing in a Mental Model Approach to Syllogistic Reasoning , 1989, IJCAI.

[18]  John A. Barnden,et al.  Semantic Networks , 1998, Encyclopedia of Social Network Analysis and Mining.

[19]  Ronald J. Brachman,et al.  An Overview of the KL-ONE Knowledge Representation System , 1985, Cogn. Sci..

[20]  Angela Schwering,et al.  Learning from Inconsistencies in an Integrated Cognitive Architecture , 2008, AGI.

[21]  K. Holyoak,et al.  The analogical mind. , 1997 .

[22]  Pascal Hitzler,et al.  Perspectives of Neural-Symbolic Integration , 2007, Studies in Computational Intelligence.

[23]  R. Goldblatt.  Topoi, the Categorial Analysis of Logic , 1979 .

[24]  Gordon Plotkin,et al.  A Note on Inductive Generalization , 2008 .

[25]  Kai-Uwe Kühnberger,et al.  Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory , 2007, Perspectives of Neural-Symbolic Integration.

[26]  Kai-Uwe Kühnberger,et al.  Metaphors and heuristic-driven theory projection (HDTP) , 2006, Theor. Comput. Sci..