Abstract
This paper concerns with the ART1 (Adaptive Resonance Theory 1) in Neural Network. Important features of ART1 are similarity measure (criterion), vigilance parameter (ρ), and their function to classify the input patterns. Experimental results show that the similarity measure as designed originally does not increase the number of categories with the increased value of ρ but decreases, too. This is against the claim of ‘stability-plasticity’ dilemma. A number of researchers have considered this and suggested alternative similarity measures. Here, we propose a new similarity criterion which eliminates this problem and also possesses the property of lowest list presentations needed for self stabilization of the network. We compare the results of different similarity criteria experimentally and present them in graphs. Analysis of the network under noisy environment is also carried out.
Similar content being viewed by others
References
G.A. Carpenter and S. Grossberg, “A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine”, Computer Vision, Graphics and Image Processing, Vol. 37, pp. 54–115, 1987.
M.M.A. Hashem, “Adaptive Resonance Theory: Characterization of ART1 and Development of Similarity Measure”, Master Thesis Asian Institute of Technology, Bangkok, 1993.
R. Sadananda and G.R.M. Sudhakara Rao, “ART1: Model Algorithm Characterization and New Similarity Metric Proposition in the Novelty Detector”, Proc. IEEE Neural Network Conference (Perth), Causal Productions, Australia, 1995.
E.E. Khin, “Concept Generalization in Adaptive Resonance Theory”, Master Thesis Asian Institute of Technology, Bangkok, 1996.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Khin, E.E., Shrestha, A. & Sadananda, R. ART1: Similarity Measures. Neural Processing Letters 6, 109–117 (1997). https://doi.org/10.1023/A:1009619908131
Issue Date:
DOI: https://doi.org/10.1023/A:1009619908131