BoltzCONS: dynamic symbol structures in a connectionist network
Artificial Intelligence - On connectionist symbol processing
Mapping part-whole hierarchies into connectionist networks
Artificial Intelligence - On connectionist symbol processing
Recursive distributed representations
Artificial Intelligence - On connectionist symbol processing
Artificial Intelligence - On connectionist symbol processing
New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
Decision Combination in Multiple Classifier Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Shape recognition by integrating structural descriptions and geometrical/statistical transforms
Computer Vision and Image Understanding
A New Algorithm for Error-Tolerant Subgraph Isomorphism Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Algorithm for Subgraph Isomorphism
Journal of the ACM (JACM)
Inductive Logic Programming: Techniques and Applications
Inductive Logic Programming: Techniques and Applications
Unified Integration of Explicit Knowledge and Learning by Example in Recurrent Networks
IEEE Transactions on Knowledge and Data Engineering
A Shape Analysis Model with Applications to a Character Recognition System
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Logical Definitions from Relations
Machine Learning
Prototyping Structural Descriptions: An Inductive Learning Approach
SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Performance Evaluation of the VF Graph Matching Algorithm
ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Learning Structural Descriptions From Examples
Learning Structural Descriptions From Examples
Information combination operators for data fusion: a comparative review with classification
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Supervised neural networks for the classification of structures
IEEE Transactions on Neural Networks
A general framework for adaptive processing of data structures
IEEE Transactions on Neural Networks
Holographic reduced representations
IEEE Transactions on Neural Networks
Stability properties of labeling recursive auto-associative memory
IEEE Transactions on Neural Networks
A structural learning algorithm and its application to predictive toxicology evaluation
BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
| Hi-index | 0.00 |
During the last two decades, the attempts of finding effective and efficient solutions to the problem of learning any kind of structured information have been splitting the scientific community. A 驴holy war驴 has been fought between the advocates of a symbolic approach to learning and the advocates of a connectionist approach. One of the most repeated claims of the symbolic party has been that symbolic methods are able to cope with structured information while connectionist ones are not. However, in the last few years, the possibility of employing connectionist methods for structured data has been widely investigated and several approaches have been proposed. Does this mean that the connectionist partisans are about to win the ultimate battle? Is connectionism the 驴One True Approach驴 to knowledge learning? The paper discusses this topic and gives an experimental answer to these questions. In details, first, a novel algorithm for learning structured descriptions, ascribable to the category of symbolic techniques, is proposed. It faces the problem directly in the space of graphs by defining the proper inference operators, as graph generalization and graph specialization, and obtains general and consistent prototypes with a low computational cost with respect to other symbolic learning systems. Successively, the proposed algorithm is compared with a recent connectionist method for learning structured data [17] with reference to a problem of handwritten character recognition from a standard database publicly available on the Web. Finally, after a discussion highlighting pros and cons of symbolic and connectionist approaches, some conclusions, quantitatively supported by the experimental data, are drawn. The orthogonality of the two approaches strongly suggests their combination in a multiclassifier system so as to retain the strengths of both of them, while overcoming their weaknesses. The results on the experimental case-study demonstrated that the adoption of a parallel combination scheme of the two algorithms could improve the recognition performance of about 10 percent. A truce or an alliance between the symbolic and the connectionist worlds?