Tsang, E.P.K. & Wang, C.J., A Generic Neural Network Approach for Constraint Satisfaction Problems. In Taylor, J.G. (ed.), Neural network applications, Springer-Verlag, 1992, 12-22.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....if C basic (v ( greedy select(v end while return no satisfying assignment found 2.4. 2 GENET GENET for constraint satisfaction problems is an approach for constraint satisfaction using a representation of a CSP as a neural net (see for example [44] developed by Wang and Tsang [7, 60, 62]. The method comes in two avors depending on if only binary or k ary constraints are to be allowed. GENET for binary CSP s In this model, each label hx; vi is represented by a node in the network, and each set of exactly two labels fhx; vi; hy; wig that are incompatible with respect to a ....

Tsang, E., and Wang, C. A generic neural network approach for constraint satisfaction problems. Springer-Verlag, 1992.

....recent interest in applying ANN to optimization and CSP. For examples, Hopfield network, the Boltzmann Machine and the elastic network have been used in the traveling salesman problems [15, 1, 10] the Tangram puzzles [19] and the N queens problem [25] with satisfactory results. Wang and Tsang [32, 28] propose GENET, a generic ANN model, for solving general CSP s with binary constraints. A massively parallel implementation of GENET may attain a theoretical speedup in the order of 10 8 over sequential heuristic search. Wang and Tsang [33] also propose a cascadable VLSI design for GENET. ANN, ....

....neural network has as answer. We say that the neural network model is probabilistically complete. 4. Incrementality) The model must be amenable to efficient incremental execution. Any ANN model that satisfies the above properties can be used in our framework. We have chosen the GENET model [32, 28] to demonstrate the feasibility of our proposal. In the following, we give a brief introduction to GENET and show how we adapt the execution model of GENET to an incremental version. At appropriate places, we explain why GENET satisfies the three criteria. 2.1 GENET GENET [32, 28] is a generic ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....recent interest in applying ANN to optimization and CSP. For examples, Hopfield network, the Boltzmann Machine and the elastic network have been used in the traveling salesman problems [18, 1, 13] the Tangram puzzles [23] and the N queens problem [34] with satisfactory results. Wang and Tsang [43, 39] propose GENET, a generic ANN model, for solving general CSP s with binary constraints. Wang and Tsang [44] also propose a cascadable VLSI design for GENET. A VLSI implementation of GENET would provide a potential speed gain in an order of 10 6 to 10 8 over existing CSP languages running on ....

....ANN models are probabilistic in nature. 4. Incrementality) Adding new constraints to an existing solvable set of constraints is a frequent and primitive step in a CLP system. Thus the model must be amenable to efficient incremental execution. 2. 3 GENET: a Generic Neural Network Model GENET [43, 39] is a generic neural network simulator designed to solve binary CSP s with finite domains. It has also been applied to solve general CSP s such as the car sequencing problem [8] We describe the network structure and the convergence procedure of GENET. Then we explain the behavior of GENET s ....

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....the worst case. Constraint logic programming systems has been successfully used to tackle a number of industrial CSP applications such as car sequencing [3] disjunctive scheduling [18] and firmware design [4] Stochastic search methods have also had remarkable success in solving industrial CSP s [16] and CSP optimization problems [1, 7] Constraint logic programming systems use a constraint solver to direct a search for an answer to goal. When the constraint solver determines that the constraints collected on some derivation path are unsatisfiable, the CLP system backtracks and tries a ....

....derivation, the issues dealt with in this paper do not arise. This paper is organised as follows. Section 2 briefly introduces some preliminaries for subsequent discussion. Section 3 describes how a stochastic solver can be used within a CLP system. In section 4, we briefly describe the GENET [2, 16, 19] model which is a probabilistic artificial neural networks (ANN) used as the constraint solver to demonstrate the feasibility of our approach. We show how we adopt the original model to support efficient incremental execution with backtracking on constraints. Section 5 describes our experimental ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....the worst case. Constraint logic programming systems have been successfully used to tackle a number of industrial CSP applications such as car sequencing [3] disjunctive scheduling [14] and firmware design [4] Stochastic search methods have also had remarkable success in solving industrial CSP s [13] and constraint satisfaction optimisation problems (CSOPs) 1, 5] Constraint logic programming systems use a constraint solver to direct a search for an answer to goal. When the constraint solver determines that the constraints collected on some derivation path are unsatisfiable, the CLP system ....

....Section 2 briefly introduces some preliminaries for subsequent discussion. Section 3 describes various models for how a stochastic solver can be used within a CLP system, while Section 4 gives soundness and completeness results for these various models. In section 5, we briefly describe the GENET [13, 2] model which is a probabilistic artificial neural networks (ANN) used as the constraint solver to demonstrate the feasibility of our approach. We describe how we adopt the original model to support efficient incremental execution with backtracking on constraints. Section 6 gives our experimental ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, 12--22. Springer-Verlag, 1992.

....the worst case. Constraint logic programming systems have been successfully used to tackle a number of industrial CSP applications such as car sequencing [4] disjunctive scheduling [19] and firmware design [5] Stochastic search methods have also had remarkable success in solving industrial CSP s [18] and constraint satisfaction optimisation problems (CSOP s) 1, 6] Constraint logic programming systems use a constraint solver to direct a search for an answer to goal. When the constraint solver determines that the constraints collected on some derivation path are unsatisfiable, the CLP system ....

....Section 2 briefly introduces some preliminaries for subsequent discussion. Section 3 describes various models for how a stochastic solver can be used within a CLP system, while Section 4 gives soundness and completeness results for these various models. In section 5, we briefly describe the GENET [18, 3] model which is a probabilistic artificial neural networks(ANN) used as the constraint solver to demonstrate the feasibility of our approach. We describe how we adapt the original model to support efficient incremental execution with backtracking on constraints. Section 6 gives our experimental ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, 12--22. Springer-Verlag, 1992.

....been recent interest in applying ANN to optimization and CSP. For examples, Hopfield network, the Boltzmann Machine and the elastic network have been used in the traveling salesman problems [12, 1, 8] the Tangram puzzles [15] and the N queens problem [21] with satisfactory results. Wang and Tsang [26, 22] proposed GENET, a generic ANN model, for solving general CSP s with binary constraints. A massively parallel implementation of GENET may attain a theoretical speedup in the order of 10 8 over sequential heuristic search. Wang and Tsang [27] also proposed a cascadable VLSI design for GENET. ....

....neural network has as answer. We say that the neural network model is probabilistically complete. 3. Incrementality) The model must be amenable to efficient incremental execution. Any ANN model that satisfies the above properties can be used in our framework. We have chosen the GENET model [26, 22] to demonstrate the feasibility of our proposal. In the following, we give a brief introduction to GENET and show how we adapt the execution model of GENET to an incremental version. Our statistics shows that the incremental version is at least as efficient as the batch version. At appropriate ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

.... a number of industrial CSP applications such as car sequencing [3] disjunctive scheduling [12] and firmware design [4] Local search methods, such as simulated annealing, artificial neural networks (ANNs) and evolutionary algorithms, have also had remarkable success in solving industrial CSPs [11] and CSP optimization problems [1] 5] Among the local search based constraint solvers, GENET [11] 13] is an ANN to solve binary CSPs with finite domains. It has been shown to be efficient for solving certain hard or large instances of CSPs [13] 2] GENET has been enhanced in a number of ....

.... firmware design [4] Local search methods, such as simulated annealing, artificial neural networks (ANNs) and evolutionary algorithms, have also had remarkable success in solving industrial CSPs [11] and CSP optimization problems [1] 5] Among the local search based constraint solvers, GENET [11], 13] is an ANN to solve binary CSPs with finite domains. It has been shown to be efficient for solving certain hard or large instances of CSPs [13] 2] GENET has been enhanced in a number of ways. It was augmented to handle atmost and illegal constraints in order to solve carsequencing ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, 12--22. Springer-Verlag, 1992.

.... used to tackle a number of industrial CSP applications such as car sequencing [3] disjunctive scheduling [13] and firmware design [4] Stochastic search methods, such as simulated annealing, neural networks and evolutionary algorithms, have also had remarkable success in solving industrial CSP s [12] and CSP optimization problems [1, 5] Among the stochastic solvers, GENET [12, 14] is a neural network simulator to solve binary CSP s with finite domains. It is shown to be efficient for solving certain hard or large instances of CSP s [14, 2] GENET has been enhanced in a number of ways. It ....

.... [3] disjunctive scheduling [13] and firmware design [4] Stochastic search methods, such as simulated annealing, neural networks and evolutionary algorithms, have also had remarkable success in solving industrial CSP s [12] and CSP optimization problems [1, 5] Among the stochastic solvers, GENET [12, 14] is a neural network simulator to solve binary CSP s with finite domains. It is shown to be efficient for solving certain hard or large instances of CSP s [14, 2] GENET has been enhanced in a number of ways. It was augmented to handle atmost and illegal constraints in order to solve ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, 12--22. Springer-Verlag, 1992.

....useful to others using GENET to solve large dicult constraint satisfaction problems and in particular problems with similar optimisation criteria. 3 Description of GENET GENET is based on a software simulation of a Neural Network. It was designed at Essex University and is introduced in [18] and [16]. It is an iterative improvement technique using the principle of the min con icts heuristic [13] Tsang and Wang [18, 16] in 1991 and 1992 showed the success of GENET in solving binary CSPs. In 1994 Davenport and Tsang [5] enhanced GENET so it could handle some non binary constraints. Lee et al. ....

....optimisation criteria. 3 Description of GENET GENET is based on a software simulation of a Neural Network. It was designed at Essex University and is introduced in [18] and [16] It is an iterative improvement technique using the principle of the min con icts heuristic [13] Tsang and Wang [18, 16] in 1991 and 1992 showed the success of GENET in solving binary CSPs. In 1994 Davenport and Tsang [5] enhanced GENET so it could handle some non binary constraints. Lee et al. 12] have also proposed a system for adapting GENET for general non binary constraints, but the system developed by ....

[Article contains additional citation context not shown here]

E. P. K. Tsang and C. J. Wang. A generic neural network approach for constraint satisfaction problems. Neural Network Applications, pages 12-22, 1992.

....the worst case. Constraint logic programming systems has been successfully used to tackle a number of industrial CSP applications such as car sequencing [3] disjunctive scheduling [13] and firmware design [4] Stochastic search methods have also had remarkable success in solving industrial CSP s [12] and CSP optimization problems [1, 5] Constraint logic programming systems use a constraint solver to direct a search for an answer to goal. When the constraint solver determines that the constraints collected on some derivation path are unsatisfiable, the CLP system backtracks and tries a ....

....derivation, the issues dealt with in this paper do not arise. This paper is organised as follows. Section 2 briefly introduces some preliminaries for subsequent discussion. Section 3 describes how a stochastic solver can be used within a CLP system. In section 4, we briefly describe the GENET [2, 12, 14] model which is a probabilistic artificial neural networks(ANN) used as the constraint solver to demonstrate the feasibility of our approach. We show how we adopt the original model to support efficient incremental execution with backtracking on constraints. Section 5 describes our experimental ....

[Article contains additional citation context not shown here]

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....are performed in parallel, and eventually the network should stabilize in some state. The network is trained by adjusting the weights of the interconnections. KCL. KCL obtained promising results using GENET, a generic connectionist tool which simulates neural networks on a sequential computer [31]. Originally developed for constraint satisfaction problems, GENET was adapted by Vom Scheidt [33] to the problem at hand. An instance of the minimum interference problem is represented by a network, each link corresponding to a cluster of vertices, with one vertex for each frequency in its ....

E. P. K. Tsang, C. J. Wang (1992). A generic neural network approach for constraint satisfaction problems. J. Taylor (ed.). Neural Network Applications, Springer, Berlin, 12-22.

....uses a minimal number of distinct frequencies (Starting Point Selection Strategy for Frequency Minimisation in [9] Tabu Search results are tabulated with the GENET results in x4:4. 4 GENET GENET is a connectionist approach to constraint satisfaction problems developed by Dr E.P.K. Tsang et al. [10]. An implementation of the algorithm was used to solve the Radio Link Frequency Assignment Problem presented in the CALMA data set [6] It was extended to also handle constraint optimisation problems and modifications of the escape heuristic and optimisations of the search mechanism that ....

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In J.G. Taylor, editor, Neural network applications, pages 12--22. Springer-Verlag, 1992.

....the taboo list, while Genet uses a scheme of dynamic local penalization to fill up local minima and discourage incompatible assignments. Both approaches will be explained in the next sections. 2.1 GENET 2.1. 1 Introduction Genet is a connectionist approach to CSPs developed by Tsang and Wang [1]. The problem representation in Genet derives from its neural network interpretation. A recurrent network with weighted inhibitory connections encodes the variables and constraints characterizing the problem instance. The network alternatingly settles into stable states corresponding to minima of ....

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In J.G. Taylor, editor, Neural network applications, pages 12--22. Springer-Verlag, 1992.

....can be formalized as DCSOPs, and in turn DCSOPs can provide a formal framework for studying DAI methods. Various distributed approaches have been used to solve these problems; however, most of them used tree search techniques (such as [9, 13] and only a few were repair based algorithms (such as [15, 8]) though the repair based ones are mostly distributed techniques for solving CSPs and not specifically designed for DCSOPs (naturally distributed problems) In this paper, we propose a generic distributed repair based algorithm for solving DCSOPs. 2 Background Our algorithm was motivated by two ....

E. Tsang and C. J. Wang. A Generic Neural Network Approach for Constraint Satisfaction Problems. In Neural Network Applications, pages 12--22, 1992.

....applying ANN to CSP s and constraint optimization problems. For examples, Hopfield network, the Boltzmann Machine and the elastic network have been used in the traveling salesman problems [18, 1, 13] the Tangram puzzles [23] and the N queens problem [34] with satisfactory results. Wang and Tsang [43, 39] propose GENET, a generic ANN model, for solving general CSP s with binary constraints. Wang and Tsang [44] also propose a cascadable VLSI design for GENET. A VLSI implementation of GENET would provide a potential speed gain in an order of 10 6 to 10 8 over existing CSP languages running on ....

....ANN models are probabilistic in nature. 4. Incrementality) Adding new constraints to an existing solvable set of constraints is a frequent and primitive step in a CLP system. Thus the model must be amenable to efficient incremental execution. 2. 3 GENET: a Generic Neural Network Model GENET [43, 39] is a generic neural network simulator designed to solve binary CSP s with finite domains. It has also been applied to solve general CSP s such as the car sequencing problem [8] We describe the network structure and the convergence procedure of GENET. Then we explain the behavior of GENET s ....

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....been recent interest in applying ANN to optimization and CSP. For examples, Hopfield network, the Boltzmann Machine and the elastic network have been used in the traveling salesman problems [9, 1, 6] the Tangram puzzles [12] and the Nqueens problem [15] with satisfactory results. Wang and Tsang [19, 17] propose GENET, a generic ANN model, for solving general CSP s with binary constraints. A massively parallel implementation of GENET may attain a theoretical speedup in the order of 10 8 over sequential heuristic search. Wang and Tsang [20] also propose a cascadable VLSI design for GENET. ANN, ....

....nature of PROCLANN to the fullest extent. It means that if the CSP specified by the program is solvable, then there always exists a successful derivation and the answer network obtained has non zero probability to converge to any solution of the CSP. 4 GENET We have chosen the GENET model [19, 17] to demonstrate the feasibility of our proposal. GENET is a generic neural network simulator that can be used to solve general CSP s with finite domains. To illustrate how a GENET network is constructed for a CSP, let us take a simple but tight 2 binary CSP as example. Assume there are five ....

E.P.K. Tsang and C.J. Wang. A generic neural network approach for constraint satisfaction problems. In G Taylor, editor, Neural Network Applications, pages 12--22. Springer-Verlag, 1992.

....D;C f ) the constraints in C f has a range of return values from 0 to 1. Obviously, CSP is a restricted instance of FCSP. The domain of problems that CSP can model is a subset of the problems that FCSP can model. A generic neural network model called GENET has been proposed by Tsang and Wang [2] for solving CSP s with binary constraints. GENET solves CSP s by iterative improvement and incorporates a learning strategy to escape local minima. Lee, Leung and Won [3] later propose E GENET, an extended GENET to solve non binary CSP s. We have also developed a model called fuzzy GENET based ....

Tsang, E. P. K., Wang, C. J.: A Generic Neural Network Approach For Constraint Satisfaction Problem. Neural Network Applications (1992) 12--22

....penalty method forming an algorithm that performs well on standard benchmark optimization problems. We compare the hybrid algorithm with the Petford and Welsh algorithm [5] MFA at a constant temperature[7] and a stochastic weight penalty technique, known as GENET, proposed by Tsang Wang (1992) [8]. 1 Introduction Constraint satisfaction problems such as the Traveling Salesman Problem (TSP) Graph Bipartitioning and Graph Colouring have been used extensively for bench marking new optimization algorithms. The possibility of mapping these problems onto Neural Networks has increased research ....

....replace the stochastic update of SA with deterministic mean field theory equations. Again they use a pseudo temperature parameter with a cooling schedule and reported speed up factors of up to 30 over SA, with only a slight reduction in solution quality. The GENet al..gorithm, Tsang Wang (1992) [8]) is a stochastic technique comprising two stages. Gradient descent has control initially until the system stabilizes in a minimum. If trapped in a non zero energy state, a breakout method takes over. This breakout method, proposed by Morris in 1993 [3] uses a weight penalty matrix to penalise ....

E.P.K. Tsang, C.J. Wang. (1992) A Generic Neural Network Approach For Constraint Satisfaction Problems. In J.G.Taylor (ed.), Neural Network Applications, Springer-Verlag, 1992, p.12-22.

No context found.

Tsang, E.P.K. & Wang, C.J., A Generic Neural Network Approach for Constraint Satisfaction Problems. In Taylor, J.G. (ed.), Neural network applications, Springer-Verlag, 1992, 12-22.

No context found.

Tsang, E.P.K. & Wang, C.J., A generic neural network approach for constraint satisfaction problems, in Taylor, J.G. (ed.), Neural network applications, Springer-Verlag, 1992, 12-22

No context found.

Tsang, E.P.K. & Wang, C.J., A generic neural network approach for constraint satisfaction problems, in Taylor, J.G. (ed.), Neural network applications, Springer-Verlag, 1992, 12-22

No context found.

Tsang, E.P.K. & Wang, C.J., A generic neural network approach for constraint satisfaction problems, in Taylor, J.G. (ed.), Neural network applications, SpringerVerlag, 1992, 12-22

....K. Pulse Density Modulation Technique in VLSI Implementations of Neural Network Algorithms , IEEE J. of Solid State Circuits, vol. 25, no. 5, pp. 1277 1286, Oct. 1990. Tsang, E.P.K. The consistent labelling problem in temporal reasoning , Proc. AAAI Conference, Seattle, pp. 251 255, July 1987. Tsang, E. P. K. Wang, C. J. A generic neural network approach for constraint satisfaction problems , Proc. NCM 91 Applications of Neural Networks, to be published in Series in Neural Networks by Springer Verlag, 1992. Waltz, D.L. Understanding line drawings of scenes with shadows , in WINSTON, P.H. ed. The Psychology ....

Tsang, E. P. K., & Wang, C. J., "A generic neural network approach for constraint satisfaction problems", Proc. NCM'91 Applications of Neural Networks, to be published in Series in Neural Networks by Springer Verlag, 1992.

....K. Pulse Density Modulation Technique in VLSI Implementations of Neural Network Algorithms , IEEE J. of Solid State Circuits, vol. 25, no. 5, pp. 1277 1286, Oct. 1990. Tsang, E.P.K. The consistent labelling problem in temporal reasoning , Proc. AAAI Conference, Seattle, pp. 251 255, July 1987. Tsang, E. P. K. Wang, C. J. A generic neural network approach for constraint satisfaction problems , Proc. NCM 91 Applications of Neural Networks, to be published in Series in Neural Networks by Springer Verlag, 1992. Waltz, D.L. Understanding line drawings of scenes with shadows , in WINSTON, P.H. ed. The Psychology ....

Tsang, E. P. K., & Wang, C. J., "A generic neural network approach for constraint satisfaction problems", Proc. NCM'91 Applications of Neural Networks, to be published in Series in Neural Networks by Springer Verlag, 1992.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC