Arpita Shah
ABSTRACT
Two connectionist techniques are applied to real world insurance policy data. Multi Layer Perceptrons are trained to categorise data using a variant of back propagation called Back Percolation. Self Organising Maps are also used; as they are a clustering algorithm, a semi-supervised algorithm is used to modify the system so that it categorises. On this particular data set, the modified SOM system gets 196 out of the 238 positive results significantly outperforming the Multi-Layer Perceptron, which gets 35. Moreover, the SOM system outperforms the best prior system, a Bayesian model, which got only 121.
- THE UCI KDD ARCHIVE, (2000), University of California Available from: http://kdd.ics.uci.edu/databases/tic/tic.html {Accessed on 12/07/2007}Google Scholar
- Mark Jurik, BackPercolation, (1994), Available from: http://www.jurikres.com/faq/reports.htm#top {Accessed 24/03/2007}Google Scholar
- M. Minsky, Kohonen Self Organizing Feature Maps (2007) Available from: http://www.ai-junkie.com/ann/som/som1.html {Accessed 28/01/2007}Google Scholar
- P. Kontkanen (2000) CoIL 2000 submission. (June 22 2000) Published by Sentient Machine Research, Amsterdam and Leiden Institute of Advanced Computer Science, Leiden. Available from: http://www.liacs.nl/~putten/library/cc2000/KONTKA~1.pdf {Access 12/09/2007}Google Scholar
- P. van der Putten and M. van Someren (2000) Published by Sentient Machine Research, Amsterdam and Leiden Institute of Advanced Computer Science, Leiden. Available from: http://www.liacs.nl/~putten/library/cc2000/report2.html {Access 01/08/2006}Google Scholar
- A. Greenyer (2000) Coil 2000: The use of a learning classifier system JXCS. Published by Sentient Machine Research, Amsterdam and Leiden Institute of Advanced Computer Science, Leiden. Available from: http://www.liacs.nl/~putten/library/cc2000/GREENY~1.pdf {Access 12/09/2007}Google Scholar
- D. Rumelhart and J. McClelland. (1986) Parallel Distributed Processing. MIT Press.Google Scholar
- T. Kohonen, (1997) Self-Organizating Maps, New York: Springer-Verlag. Google ScholarDigital Library
- T. Germano, Self Organizing Map (2007) Available from: http://davis.wpi.edu/~matt/courses/soms/ {Accessed 29/01/2007}Google Scholar
- D. Rumelhart, G. Hinton, and R. Williams (1986) Learning Interanal Representations of Error Propagation. In Parallel Distributed Processing vol 1. Chap 8. Google ScholarDigital Library
- {wc} W. Crocoll (2000) Artificial Network Portion of Coil Study. Published by Sentient Machine Research, Amsterdam and Leiden Institute of Advanced Computer Science, Leiden. Available from: http://www.liacs.nl/~putten/library/cc2000/CROCOL~1.pdfGoogle Scholar
- U. Fayyad and G. Piatetsky-Shapiro, et al (eds.). (1996) Advances in Knowledge Discovery and Data Mining. AAAI Press, Menlo Park: CA. Google ScholarDigital Library
- Richard Holbrey, Dimension Reduction Algorithms for Data Mining and Visualization, available from: http://www.comp.leeds.ac.uk/richardh/astro/ {Accessed 07/03/07}Google Scholar
- S. Kaski. (1997)Data Exploration Using Self-Organizing Maps. Doctorate Thesis, Neural Networks Research Centre, Helsinki University of Technology.Google Scholar
Index Terms
- Categorising insurance policy data with MLPs and SOMs
Recommendations
SOM of SOMs: self-organizing map which maps a group of self-organizing maps
ICANN'05: Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part IThis paper aims to propose an extension of SOMs called an “SOM of SOMs,” or SOM2, in which the mapped objects are self-organizing maps themselves. In SOM2, each nodal unit of the conventional SOM is replaced by a function module of SOM. Therefore, SOM2 ...
SOM of SOMs: an extension of SOM from ‘map' to ‘homotopy'
ICONIP'06: Proceedings of the 13 international conference on Neural Information Processing - Volume Part IThis paper proposes an extension of an SOM called the “SOM of SOMs,” or SOM2, in which objects to be mapped are self-organizing maps. In SOM2, each nodal unit of a conventional SOM is replaced by a function module of SOM. Therefore, SOM2 can be regarded ...
SOM of SOMs
This paper proposes an extension of the self-organizing map (SOM), in which the mapping objects themselves are self-organizing maps. Thus a ''SOM of SOMs'' is presented, which we refer to as a SOM^2. A SOM^2 has a hierarchical structure consisting of a ...
Comments