Fuzzy ART has been proposed for learning stable recognition categories for an arbitrary sequence of analogue input patterns. It uses a match based learning mechanism to categorise inputs based on similarities in their features. However, this approach does not work well for neural control, where inputs have to be categorised based on the classes which they represent, rather than by the features of the input. To address this we propose and investigate ReART, a novel extension to Fuzzy ART. ReART uses a feedback based categorisation mechanism supporting class based input categorisation, online learning, and immunity from the plasticity stability dilemma. ReART is used for online control by integrating it with a separate external function which maps each ReART category to a desired output action. We test the proposal in the context of a simulated wireless data reader intended to be carried by an autonomous mobile vehicle, and show that ReART training time and accuracy are significantly better than both Fuzzy ART and Back Propagation. ReART is also compared to a Naïve Bayesian Classifier. Naïve Bayesian Classification achieves faster learning, but is less accurate in testing compared to both ReART, and Bach Propagation.
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
G. A. Carpenter, S. Grossberg. Fuzzy ART: Fast stable learning and categorization of analogue patterns by an adaptive resonance system. Neural Networks, Vol. 4, 1991, pp. 759–771
G. A. Carpenter, S. Grossberg, Adaptive resonance theory. In M.A. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks, Second Edition. Cambridge, MA: MIT, 2003, pp. 87–90
D. D. Ediriweera, I. W. Marshall, Internally self organising neural network for online learning of perception to action mappings in sensor networks, Proceedings of London Communications Symposium, 2005, pp. 21–24
C. J. Merz, D. C. St. Clair, W. E. Bond, SeMi-supervised adaptive resonance theory (SMART2). IJCNN, International Joint Conference on Neural Networks, Vol. 3, 7–11 June 1992, pp. 851–856
5.A. Weitzenfeld, M. A. Arbib, A. Alexander, Chapter Eight in the Neural Simulation Language, Cambridge, MA: MIT, ISBN: 0-262-73149-5, July 2002, pp. 157–169
G. A. Carpenter, S. Grossberg, J. H. Reynolds, ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-organizing Neural Network, Neural Networks (Publication), Vol. 4, 1991, pp. 565–588
S. W. Lee. D. Palmer-Brown. C. M. Roadknight. Performance-guided neural network for rapidly self-organising active network management, Neurocomputing, special issue on Hybrid Neurocomputing, Dordrecht: Elsevier, 2004, 61C, pp. 520
A. Pérez-Uribe. A non-computationally-intensive neurocontroller for autonomous mobile robot navigation. Chapter 8 in Biologically inspired robot behaviour engineering, Series: Studies in Fuzziness and Soft Computing, Vol. 109. In R. J. Duro, J. Santos, M. Grana (Eds.), Springer, Germany, 2002, pp. 215–238
R. Beale, T. Jackson, Neural Computing: An Introduction, ISBN: 0852742622, Institute of Physics Publishing, London, UK, 1990, pp. 63–80
Rish, Irina, An empirical study of the naive Bayes classifier, IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, 2001
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer Science+Business Media B.V
About this chapter
Cite this chapter
Ediriweera, D. ., Marshall, I.W. (2009). Reinforced ART (ReART) for Online Neural Control. In: Ao, SI., Rieger, B., Chen, SS. (eds) Advances in Computational Algorithms and Data Analysis. Lecture Notes in Electrical Engineering, vol 14. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-8919-0_20
Download citation
DOI: https://doi.org/10.1007/978-1-4020-8919-0_20
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-8918-3
Online ISBN: 978-1-4020-8919-0
eBook Packages: Computer ScienceComputer Science (R0)