Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Mining competent case bases for case-based reasoning
Artificial Intelligence
A Rule-Based Object-Oriented OWL Reasoner
IEEE Transactions on Knowledge and Data Engineering
Flexible diagnosis of discrete-event systems by similarity-based reasoning techniques
Artificial Intelligence
How to use the SOINN software: user's guide (version 1.0)
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Unguided robot navigation using continuous action space
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Self-organizing incremental neural network and its application
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Hi-index | 0.00 |
An architecture for reasoning with pattern-based if-then rules is proposed. By processing patterns as real-valued vectors and classifying similar if-then rules into clusters in long-term memory, the proposed system can store pattern-based if-then rules of propositional logic, including conjunctions, disjunctions, and negations. Moreover, it achieves some important properties for intelligent systems such as incremental learning, generalization, avoidance of duplicate results, and robustness to noise. Results of experiments demonstrate that the proposed method is effective for intelligent systems for solving various tasks autonomously in a real environment.