Abstract
We propose an architecture for reasoning with pattern-based if-then rules that is effective for intelligent systems like robots solving varying tasks autonomously in a real environment. The proposed system can store pattern-based if-then rules of propositional logic, including conjunctions, disjunctions, negations, and implications. The naive pattern-based reasoning can store pattern-based if-then rules and make inferences using them. However, it remains insufficient for intelligent systems operating in a real environment. The proposed system uses an algorithm that is inspired by self-incremental neural networks such as SONIN and SOINN-AM in order to achieve incremental learning, generalization, avoidance of duplicate results, and robustness to noise, which are important properties for intelligent systems
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Shen, F., Hasegawa, O.: An Incremental Network for On-line Unsupervised Classification and Topology Learning. Neural Networks 19, 90–106 (2006)
Sudo, A., Sato, A., Hasegawa, O.: Associative Memory for Online Incremental Learning in Noisy Environments. In: Proc. of the 2005 International Joint Conference on Neural Networks (IJCNN 2005) (accepted, 2007)
Yamane, K., Hasuo, T., Suemitsu, A., Morita, M.: Pattern-based reasoning using trajectory attractors. IEICE Trans. Information and System J90-D, 933–944 (2007)
Tsukimoto, H.: Pattern Reasoning: Logical Reasoning of Neural Networks. IEICE Trans. Information and System J83-D-II, 744–753 (2000)
Fritzke, B.: A growing neural gas network learns topologies. In: Proc. of Advances in Neural Information Processing Systems (NIPS), pp. 625–632 (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sudo, A., Tsuboyama, M., Zhang, C., Sato, A., Hasegawa, O. (2008). Pattern-Based Reasoning System Using Self-incremental Neural Network for Propositional Logic. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)