A Framework for Integrating Artificial Neural Networks and Logic Programming

Many real-life problems belong to the class of constraint satisfaction problems (CSP’s), which are NP-complete, and some NP-hard, in general. When the problem size grows, it becomes difficult to program solutions and to execute the solution in a timely manner. In this paper, we present a general framework for integrating artificial neural networks and logic programming so as to provide an efficient and yet expressive programming environment for solving CSP’s. To realize this framework, we propose PROCLANN, a novel constraint logic programming language. The PROCLANN language retains the simple and elegant declarative semantics of constraint logic programming. Operationally, PROCLANN uses the standard goal reduction strategy in the frontend to generate constraints, and an efficient backend constraint-solver based on artificial neural networks. Its operational semantics is probabilistic in nature. We show that PROCLANN is sound and weakly complete. A novelty of PROCLANN is that while it is a committed-choice language, PROCLANN supports non-determinism, allowing the generation of multiple answers to a query. An initial prototype implementation of PROCLANN is constructed and demonstrates empirically that PROCLANN out-performs the state of art in constraint logic programming implementation on certain hard instances of CSP’s.

[1]  Andrew J. Davenport,et al.  GENET: A Connectionist Architecture for Solving Constraint Satisfaction Problems by Iterative Improvement , 1994, AAAI.

[2]  Boon Toh Low,et al.  Neural logic programming , 1990, [1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence.

[3]  Edward Tsang,et al.  Solving constraint satisfaction problems using neural networks , 1991 .

[4]  Mark D. Johnston,et al.  A discrete stochastic neural network algorithm for constraint satisfaction problems , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[5]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[6]  Pascal Van Hentenryck,et al.  The Constraint Logic Programming Language CHIP , 1988, FGCS.

[7]  Nicolas Beldiceanu,et al.  Constraint Logic Programming , 1997 .

[8]  Pascal Van Hentenryck.  Constraint satisfaction in logic programming , 1989, Logic programming.

[9]  Keith L. Clark,et al.  PARLOG: parallel programming in logic , 1986, ACM Trans. Program. Lang. Syst..

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

[11]  Ehud Shapiro,et al.  A subset of Concurrent Prolog and its interpreter , 1988 .

[12]  Steve Gregory,et al.  Parallel logic programming in PARLOG - the language and its implementation , 1987 .

[13]  Pascal Van Hentenryck,et al.  Applications of CHIP to industrial and engineering problems , 1988, IEA/AIE '88.

[14]  Patrick Prosser,et al.  Domain Filtering can Degrade Intelligent Backtracking Search , 1993, IJCAI.

[15]  Edward Tsang,et al.  A cascadable VLSI design for GENET , 1995 .

[16]  Oron Shagrir.  A Neural Net With Self-Inhibiting Units For The N-Queens Problem , 1992, Int. J. Neural Syst..

[17]  M. Perrett.  Using constraint logic programming techniques in container port planning , 1991 .

[18]  Pascal Van Hentenryck,et al.  Solving the Car-Sequencing Problem in Constraint Logic Programming , 1988, ECAI.

[19]  Robert M. Haralick,et al.  Increasing Tree Search Efficiency for Constraint Satisfaction Problems , 1979, Artif. Intell..

[20]  Mark D. Johnston,et al.  Learning in stochastic neural networks for constraint satisfaction problems , 1989 .

[21]  Edward P. K. Tsang,et al.  Foundations of constraint satisfaction , 1993, Computation in cognitive science.

[22]  Frank Klawonn,et al.  Neural fuzzy logic programming , 1992, IEEE Trans. Neural Networks.

[23]  Kemal Oflazer.  Solving tangram puzzles: A connectionist approach , 1993, Int. J. Intell. Syst..

[24]  Pascal Van Hentenryck,et al.  The Cardinality Operator: A New Logical Connective for Constraint Logic Programming , 1990, WCLP.

[25]  Cecilia R. Aragon,et al.  Optimization by Simulated Annealing: An Experimental Evaluation; Part II, Graph Coloring and Number Partitioning , 1991, Oper. Res..

[26]  Alan K. Mackworth.  Consistency in Networks of Relations , 1977, Artif. Intell..

[27]  Pascal Van Hentenryck,et al.  Solving Large Combinatorial Problems in Logic Programming , 1990, J. Log. Program..

[28]  Krysia Broda,et al.  Parlog for Discrete Event Simulation , 1984, ICLP.

[29]  Edward Tsang,et al.  A Generic Neural Network Approach For Constraint Satisfaction Problems , 1992 .

[30]  Patrick Prosser,et al.  HYBRID ALGORITHMS FOR THE CONSTRAINT SATISFACTION PROBLEM , 1993, Comput. Intell..

[31]  Yannick Cras.  Using Constraint Logic Programming in Services: A Few Short Tales , 1994, ILPS.

[32]  Bernard A. Nadel,et al.  Constraint satisfaction algorithms 1 , 1989, Comput. Intell..