Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Knowledge-based artificial neural networks
Artificial Intelligence
FONN: Combining First Order Logic with Connectionist Learning
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Applying ILP to Diterpene Structure Elucidation from 13C NMR Spectra
ILP '96 Selected Papers from the 6th International Workshop on Inductive Logic Programming
An Initial Experiment into Stereochemistry-Based Drug Design Using Inductive Logic Programming
ILP '96 Selected Papers from the 6th International Workshop on Inductive Logic Programming
Detecting Traffic Problems with ILP
ILP '98 Proceedings of the 8th International Workshop on Inductive Logic Programming
Multiple Predicate Learning with RTL
AI*IA '95 Proceedings of the 4th Congress of the Italian Association for Artificial Intelligence on Topics in Artificial Intelligence
Learning Logic Programs with Neural Networks
ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
Hi-index | 0.00 |
This paper presents an application of Inductive Logic Programming (ILP) and Backpropagation Neural Network (BNN) to the problem of Thai character recognition. In such a learning problem, there exist several different classes of examples; there are 77 different Thai characters. Using examples constructed from character images, ILP learns 77 rules each of which defines each character. However, some unseen character images, especially the noisy images, may not exactly match any learned rule, i.e., they may not be covered by any rule. Therefore, a method for approximating the rule that best matches the unseen data is needed. Here we employ BNN for finding such rules. Experimental results on noisy data show that the accuracy of rules learned by ILP without the help of BNN is comparable to other methods. Furthermore, combining BNN with ILP yields the significant improvement and surpasses the other methods tested in our experiment.