Logic programs, iterated function systems, and recurrent radial basis function networks

Abstract Graphs of the single-step operator for first-order logic programs—displayed in the real plane—exhibit self-similar structures known from topological dynamics, i.e., they appear to be fractals , or more precisely, attractors of iterated function systems. We show that this observation can be made mathematically precise. In particular, we give conditions which ensure that those graphs coincide with attractors of suitably chosen iterated function systems, and conditions which allow the approximation of such graphs by iterated function systems or by fractal interpolation. Since iterated function systems can easily be encoded using recurrent radial basis function networks, we eventually obtain connectionist systems which approximate logic programs in the presence of function symbols.

[1]  Krysia Broda,et al.  Symbolic knowledge extraction from trained neural networks: A sound approach , 2001, Artif. Intell..

[2]  Pascal Hitzler,et al.  Towards a Systematic Account of Different Logic Programming Semantics , 2003, KI.

[3]  Danny De Schreye,et al.  Answer Set Planning , 1999 .

[4]  Melvin Fitting,et al.  Metric Methods Three Examples and a Theorem , 1994, J. Log. Program..

[5]  Hans W. Guesgen,et al.  Connectionist Inference Systems , 1990, Dagstuhl Seminar on Parallelization in Inference Systems.

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

[7]  Michael J. Maher.  Equivalences of Logic Programs , 1988, Foundations of Deductive Databases and Logic Programming..

[8]  Pascal Hitzler,et al.  The Well-Founded Semantics Is a Stratified Fitting Semantics , 2002, KI.

[9]  Steffen Hölldobler.  Challenge problems for the integration of logic and connectionist systems , 2000, WLP.

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

[11]  Victor W. Marek,et al.  The Logic Programming Paradigm: A 25-Year Perspective , 2011 .

[12]  Krzysztof R. Apt,et al.  Logic Programming , 1990, Handbook of Theoretical Computer Science, Volume B: Formal Models and Sematics.

[13]  Zina M. Ibrahim,et al.  Advances in Artificial Intelligence , 2003, Lecture Notes in Computer Science.

[14]  Steffen Hölldobler,et al.  Approximating the Semantics of Logic Programs by Recurrent Neural Networks , 1999, Applied Intelligence.

[15]  Pascal Hitzler,et al.  A uniform approach to logic programming semantics , 2002, Theory and Practice of Logic Programming.

[16]  Marc Bezem,et al.  Characterizing Termination of Logic Programs with Level Mappings , 1989, NACLP.

[17]  Antony Browne,et al.  Connectionist inference models , 2001, Neural Networks.

[18]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[19]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[20]  J. Lloyd.  Foundations of Logic Programming , 1984, Symbolic Computation.

[21]  Pascal Hitzler,et al.  Logic programs and connectionist networks , 2004, J. Appl. Log..

[22]  Steffen Hölldobler,et al.  Towards a New Massively Parallel Computational Model for Logic Programming , 1994 .

[23]  P. Hitzler,et al.  Convergence Classes and Spaces of Partial Functions , 2003 .

[24]  A. Seda.  Topology And The Semantics Of Logic Programs , 1995 .

[25]  V. S. Subrahmanian,et al.  The Query Topology in Logic Programming , 1989, STACS.

[26]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[27]  Steffen Hölldobler,et al.  Automated Inferencing and Connectionist Models , 1993 .

[28]  Victor W. Marek,et al.  Stable models and an alternative logic programming paradigm , 1998, The Logic Programming Paradigm.

[29]  Dino Pedreschi,et al.  Reasoning about Termination of Pure Prolog Programs , 1993, Inf. Comput..

[30]  G. Palm.  Warren McCulloch and Walter Pitts: A Logical Calculus of the Ideas Immanent in Nervous Activity , 1986 .

[31]  Pascal Hitzler,et al.  A Note on the Relationships Between Logic Programs and Neural Networks , 2000, IWFM.

[32]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[33]  Jack Minker.  Foundations of deductive databases and logic programming , 1988 .

[34]  Lokendra Shastri,et al.  Advances in SHRUTI—A Neurally Motivated Model of Relational Knowledge Representation and Rapid Inference Using Temporal Synchrony , 1999, Applied Intelligence.

[35]  S. Ginsburg,et al.  Acyclic logic programs and the completeness of SLDNF-resolution , 1991 .

[36]  Danny De Schreye.  Logic programming : proceedings of the 1999 International Conference on Logic Programming , 1999 .

[37]  Pascal Hitzler,et al.  Continuity of Semantic Operators in Logic Programming and Their Approximation by Artificial Neural Networks , 2003, KI.

[38]  Paulo Ribenboim,et al.  Ultrametric Spaces and Logic Programming , 2000, J. Log. Program..

[39]  Michael F. Barnsley,et al.  Fractals everywhere , 1988 .

[40]  Pascal Hitzler,et al.  Generalized metrics and uniquely determined logic programs , 2003, Theor. Comput. Sci..

[41]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[42]  Anthony Karel Seda,et al.  On Continuous Models of Computation: Towards Computing the Distance Between (Logic) Programs , 2003, IWFM.

[43]  Gadi Pinkas,et al.  Propositional Non-Monotonic Reasoning and Inconsistency in Symmetric Neural Networks , 1991, IJCAI.

[44]  P. Hitzler.  Generalized Metrics and Topology in Logic Programming Semantics , 2001 .

[45]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[46]  T. Metin Sezgin,et al.  Continuous Models of Computation for Logic Programs: Importing Continuous Mathematics into Logic Programming's Algorithmic Foundations , 1999, The Logic Programming Paradigm.

[47]  Fred Dushin,et al.  A continuum of discrete systems , 1997, Annals of Mathematics and Artificial Intelligence.

[48]  Paulo Ribenboim,et al.  Logic programming and ultrametric spaces , 1999 .

[49]  Artur S. d'Avila Garcez,et al.  The Connectionist Inductive Learning and Logic Programming System , 1999, Applied Intelligence.