An Image Understanding System Using Attributed Symbolic Representation and Inexact Graph-Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Relational models in natural and artificial vision
Neural Computers
The structure-mapping engine: algorithm and examples
Artificial Intelligence
Models of incremental concept formation
Artificial Intelligence
On the power of neural networks for solving hard problems
Journal of Complexity
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Instance-Based Learning Algorithms
Machine Learning
A neural network model for finding a near-maximum clique
Journal of Parallel and Distributed Computing - Special issue on neural computing on massively parallel processing
Neural networks and operations research: an overview
Computers and Operations Research - Special issue on neural networks and operations research
Neural network methods in combinatorial optimization
Computers and Operations Research - Special issue on neural networks and operations research
Conceptual clustering in a first order logic representation
ECAI '92 Proceedings of the 10th European conference on Artificial intelligence
The graph isomorphism problem: its structural complexity
The graph isomorphism problem: its structural complexity
Markov random field modeling in computer vision
Markov random field modeling in computer vision
Softmax to Softassign: neural network algorithms for combinatorial optimization
Journal of Artificial Neural Networks - Special issue: neural networks for optimization
Artificial Intelligence Review - Special issue on lazy learning
Cliques, Coloring, and Satisfiability: Second DIMACS Implementation Challenge, Workshop, October 11-13, 1993
Perspective of Constraint-Based Reasoning: An Introductory Tutorial
Perspective of Constraint-Based Reasoning: An Introductory Tutorial
Experiments with Incremental Concept Formation: UNIMEM
Machine Learning
Case-Based Learning: Beyond Classification of Feature Vectors
ECML '97 Proceedings of the 9th European Conference on Machine Learning
Induction of Recursive Program Schemes
ECML '98 Proceedings of the 10th European Conference on Machine Learning
PKDD '97 Proceedings of the First European Symposium on Principles of Data Mining and Knowledge Discovery
Similarity Measures for Structured Representations
EWCBR '93 Selected papers from the First European Workshop on Topics in Case-Based Reasoning
Structural Similarity and Adaptation
EWCBR '96 Proceedings of the Third European Workshop on Advances in Case-Based Reasoning
Self Annealing: Unifying Deterministic Annealing and Relaxation Labelling
EMMCVPR '97 Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Dissimilarity Measure for Collections of Objects and Values
IDA '97 Proceedings of the Second International Symposium on Advances in Intelligent Data Analysis, Reasoning about Data
A Logical Framework for Graph Theoretical Decision Tree Learning
ILP '97 Proceedings of the 7th International Workshop on Inductive Logic Programming
A Connectionist Approach to the Distance-Based Analysis of Relational Data
IDA '97 Proceedings of the Second International Symposium on Advances in Intelligent Data Analysis, Reasoning about Data
A novel optimizing network architecture with applications
Neural Computation
IEEE Transactions on Neural Networks
Supervised neural networks for the classification of structures
IEEE Transactions on Neural Networks
Neural Networks and Structured Knowledge: Rule Extraction andApplications
Applied Intelligence
Learning of Class Descriptions from Class Discriminations: A Hybrid Approach for Relational Objects
KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Fast Winner-Takes-All Networks for the Maximum Clique Problem
KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Central Clustering of Attributed Graphs
Machine Learning
Connectionist construction of prototypes from decision trees for graph classification
Intelligent Data Analysis
MicroPsi: contributions to a broad architecture of cognition
KI'06 Proceedings of the 29th annual German conference on Artificial intelligence
A competitive winner-takes-all architecture for classification and pattern recognition of structures
GbRPR'03 Proceedings of the 4th IAPR international conference on Graph based representations in pattern recognition
Towards the unification of structural and statistical pattern recognition
Pattern Recognition Letters
| Hi-index | 0.00 |
Labeled graphs are an appropriate and popularrepresentation of structured objects in many domains. If the labelsdescribe the properties of real world objects and their relations,finding the best match between two graphs turns out to be the weaklydefined, NP-complete task of establishing a mapping between them thatmaps similar parts onto each other preserving as much as possible oftheir overall structural correspondence. In this paper, formerapproaches of structural matching and constraint relaxation byspreading activation in neural networks and the method of solvingoptimization tasks using Hopfield-style nets are combined. Theapproximate matching task is reformulated as the minimization of aquadratic energy function. The design of the approach enables theuser to change the parameters and the dynamics of the net so thatknowledge about matching preferences is included easily andtransparently. In the last section, some examples demonstrate thesuccessful application of this approach in classification andlearning in the domain of organic chemistry.