Skip past navigation to main part of page
 
Faculties : A-Z Directory : Library
--- Back to publication index

Publications of year 1994

Books

  1. Leon Sterling and Ehud Y. Shapiro. The Art of Prolog - Advanced Programming Techniques, 2nd Ed.. MIT Press, 1994.
    Keywords: agentlab.
    @book{ tag,
    Author = {Sterling, Leon and Shapiro, Ehud Y.},
    Title = {The Art of Prolog - Advanced Programming Techniques, 2nd Ed.},
    Publisher = {MIT Press},
    Keywords = {agentlab},
    Year = {1994} 
    }
    


Journal Articles and Chapters

  1. David Morley, Michael P. Georgeff, and Anand S. Rao. A Monotonic Formalism for Events and Systems of Events. Journal of Logic and Computation, 4(5):701-720, 1994.
    Keywords: agentlab, model theory, procedural reasoning.
    @article{ tag,
    Author = {Morley, David and Georgeff, Michael P. and Rao, Anand S.},
    Title = {A Monotonic Formalism for Events and Systems of Events},
    Journal = {Journal of Logic and Computation},
    Volume = {4},
    Number = {5},
    Pages = {701-720},
    Keywords = {agentlab, model theory, procedural reasoning},
    Year = {1994} 
    }
    


  2. A. R. Pearce, T. Caelli, and W. F. Bischof. Rulegraphs for graph matching in pattern recognition. Pattern Recognition, 27(9):1231-47, 1994.
    Keywords: graph theory, machine learning, agentlab.

    Abstract: In pattern recognition, the graph matching problem involves the matching of a sample data graph with the subgraph of a larger model graph where vertices and edges correspond to pattern parts and their relations. In this paper, we present rulegraphs, a new method that combines the graph matching approach with rule-based approaches from machine learning. This new method reduces the cardinality of the (NP-complete) graph matching problem by replacing model part, and their relational attribute states, by rules which depict attribute bounds and evidence for different classes. We show how rulegraphs, when combined with techniques for checking feature label-compatibilities, not only reduce the search space but also improve the uniqueness of the matching process. (37 References).
    [download paper ]
    @article{ tag,
    Author = {Pearce, A. R. and Caelli, T. and Bischof, W. F.},
    Title = {Rulegraphs for graph matching in pattern recognition},
    Journal = {Pattern Recognition},
    Volume = {27},
    Number = {9},
    Pages = {1231-47},
    Abstract = {In pattern recognition, the graph matching problem involves the matching of a sample data graph with the subgraph of a larger model graph where vertices and edges correspond to pattern parts and their relations. In this paper, we present rulegraphs, a new method that combines the graph matching approach with rule-based approaches from machine learning. This new method reduces the cardinality of the (NP-complete) graph matching problem by replacing model part, and their relational attribute states, by rules which depict attribute bounds and evidence for different classes. We show how rulegraphs, when combined with techniques for checking feature label-compatibilities, not only reduce the search space but also improve the uniqueness of the matching process. (37 References).},
    URL = {http://www.agentlab.unimelb.edu.au/papers/pearce1994b.pdf},
    Keywords = {graph theory, machine learning, agentlab},
    Year = {1994} 
    }
    


  3. A. R. Pearce, T. Caelli, and W. F. Bischof. Learning relational structures: applications in computer vision. Applied Intelligence, 4(3):257-68, 1994.
    Note: Netherlands.
    Keywords: graph theory, machine learning, agentlab.

    Abstract: We present and compare two new techniques for learning relational structures (RSs) as they occur in 2D pattern and 3D object recognition. These techniques, namely, evidence-based networks (EBS-NNets) and Rulegraphs combine techniques from computer vision with those from machine learning and graph matching. The EBS-NNet has the ability to generalize pattern rules from training instances in terms of bounds on both unary (single part) and binary (part relation) numerical features. It also learns the compatibilities between unary and binary feature states in defining different pattern classes. Rulegraphs check this compatibility between unary and binary rules by combining evidence theory with graph theory. The two systems are tested and compared using a number of different pattern and object recognition problems. (21 References).
    [download paper ]
    @article{ tag,
    Author = {Pearce, A. R. and Caelli, T. and Bischof, W. F.},
    Title = {Learning relational structures: applications in computer vision},
    Journal = {Applied Intelligence},
    Volume = {4},
    Number = {3},
    Pages = {257-68},
    Note = {Netherlands.},
    Abstract = {We present and compare two new techniques for learning relational structures (RSs) as they occur in 2D pattern and 3D object recognition. These techniques, namely, evidence-based networks (EBS-NNets) and Rulegraphs combine techniques from computer vision with those from machine learning and graph matching. The EBS-NNet has the ability to generalize pattern rules from training instances in terms of bounds on both unary (single part) and binary (part relation) numerical features. It also learns the compatibilities between unary and binary feature states in defining different pattern classes. Rulegraphs check this compatibility between unary and binary rules by combining evidence theory with graph theory. The two systems are tested and compared using a number of different pattern and object recognition problems. (21 References).},
    URL = {http://www.agentlab.unimelb.edu.au/papers/pearce1994.pdf},
    Keywords = {graph theory, machine learning, agentlab},
    Year = {1994} 
    }
    


  4. L. Sonenberg and R. Topor. A preferred model semantics for inheritance networks. Methods of Logic in Computer Science, 1(1):3-18, 1994.
    Note: USA.
    Keywords: agentlab.

    Abstract: We describe a representation of inheritance networks with strict and defeasible links as first-order theories in which different priority policies can be expressed within the theory. We present a "preferred model" semantics for such theories by adapting the perfect model semantics for logic programs, and briefly discuss relationships between this semantics and other proposed semantics for inheritance networks. (26 References).

    @article{ tag,
    Author = {Sonenberg, L. and Topor, R.},
    Title = {A preferred model semantics for inheritance networks},
    Journal = {Methods of Logic in Computer Science},
    Volume = {1},
    Number = {1},
    Pages = {3-18},
    Note = {USA.},
    Abstract = {We describe a representation of inheritance networks with strict and defeasible links as first-order theories in which different priority policies can be expressed within the theory. We present a "preferred model" semantics for such theories by adapting the perfect model semantics for logic programs, and briefly discuss relationships between this semantics and other proposed semantics for inheritance networks. (26 References).},
    Keywords = {agentlab},
    Year = {1994} 
    }
    


Conference Proceedings

  1. David Kinny, Ljungberg, Anand Rao, Liz Sonenberg, Gil Tidhar, and Werner. Planned Team Activity. In MAAMAW 1992: Artificial Social Systems, LNCS 830, pages 227-256, 1994.
    Keywords: agentlab, teamwork.
    @inproceedings{ tag,
    Author = {Kinny, David and Ljungberg and Rao, Anand and Sonenberg, Liz and Tidhar, Gil and Werner},
    Title = {Planned Team Activity},
    BookTitle = {MAAMAW 1992: Artificial Social Systems, LNCS 830},
    Pages = {227-256},
    Keywords = {agentlab, teamwork},
    Year = {1994} 
    }
    


Tehnical Reports

  1. T. Gabric, Howden, Emma Norling, Gil Tidhar, and Liz Sonenberg. Multi-agent Design of a Traffic Flow Control System. Technical Report 94/24, Department of Computer Science, University of Melbourne, Australia, 1994.
    Keywords: agentlab.
    @techreport{ tag,
    Author = {Gabric, T. and Howden and Norling, Emma and Tidhar, Gil and Sonenberg, Liz},
    Title = {Multi-agent Design of a Traffic Flow Control System},
    Institution = {Department of Computer Science, University of Melbourne, Australia},
    Number = {94/24},
    Type = {Technical Report},
    Keywords = {agentlab},
    Year = {1994} 
    }
    



Back to publication index



Disclaimer: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Bibliography last modified: Tue Aug 21 12:15:11 2012 translated from BibTEX by bibtex2html
top of pagetop of page

Contact us

Contact the University : Disclaimer & Copyright : Privacy : Accessibility