Using genetic algorithms for an optical thin-film learning model

Please note that this is a searchable PDF derived via optical character recognition (OCR) from the original source document. As the OCR process is never 100% perfect, there may be some discrepancies between the document image and the underlying text.A novel connectionist architecture based on an optical thin-film multilayer model (OTFM) is described. The architecture is explored as an alternative to the widely used neuron-inspired models, with the thin-film thicknesses serving as adjustable ‘weights’ for the computation. The use of genetic algorithms for training the thin-film model, along with experimental results on the parity problem and the iris data classification are presented.Unpublished[1] Goldberg, D.E., Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley, 1989. [2] Purvis, M.K. and Xiaodong, L., "Connectionist Computations Based on an Optical Thin-Film Model", Proceedings of the First New Zealand Intemational Two Stream Conference on Artificial Neural Networks and Expert Systems. IEEE Computer Society Press, Los Alamitos, Califomia,pp.130-133, 1993. [3] Purvis, M.K. and Li, X., "Cormectionist Learning Using Optical Thin-Film Model", Proceedings of the 2nd New Zealand Intemational Two-Stream Conference on Artificial Neural Networks and Expert Systems, IEEE Computer Society Press, Los Alamitos, California,pp.63-66, 1995. [4] Case, W. E., "New Synthesis Method for Optical Thin-film Coatings", Applied Optics, 22:24, pp. 4111-4117, 1983. [5] Smith, R.E., Goldberg, D.E. and Earickson J.A., "SGA-C: A C-language Implementation of a Simple Genetic Algorithm", TCGA ReportNo. 91002, The University of Alabama, 1994. [6] Anderson, E., "The Irises of the Gaspe Peninsula", Bulletin of the American Iris Society, vol 59, pp. 2-5. [7] Ripley,B. D., "Statistical Aspects of Neural Networks" in Networks and Chaos -- Statistical and Probabilistic Aspects. Chapman and Hall, London, pp. 40-123, 1993. [8] Hart, A., "Using Neural Networks for Classification Tasks -- Some Experiments on Datasets and Practical Advice", J. Opl. Res. Soc., vol. 43, pp. 215-226, 1992