Show simple item record

dc.contributor.authorPurvis, Martinen_NZ
dc.contributor.authorLi, Xiaodongen_NZ
dc.date.available2011-04-07T03:05:13Z
dc.date.copyright1996-08en_NZ
dc.identifier.citationPurvis, M., & Li, X. (1996). A connectionist computational architecture based on an optical thin-film model (Information Science Discussion Papers Series No. 96/14). University of Otago. Retrieved from http://hdl.handle.net/10523/852en
dc.identifier.urihttp://hdl.handle.net/10523/852
dc.descriptionPlease 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.en_NZ
dc.description.abstractA novel connectionist architecture that differs from conventional architectures based on the neuroanatomy of biological organisms is described. The proposed scheme is based on the model of multilayered optical thin-films, with the thicknesses of the individual thin-film layers serving as adjustable ‘weights’ for the training. A discussion of training techniques for this model and some sample simulation calculations in the area of pattern recognition are presented. These results are shown to compare with results when the same training data are used in connection with a feed-forward neural network with back propagation training. A physical realization of this architecture could largely take advantage of existing optical thin-film deposition technology.en_NZ
dc.format.mimetypeapplication/pdf
dc.publisherUniversity of Otagoen_NZ
dc.relation.ispartofseriesInformation Science Discussion Papers Seriesen_NZ
dc.subject.lcshQA76 Computer softwareen_NZ
dc.titleA connectionist computational architecture based on an optical thin-film modelen_NZ
dc.typeDiscussion Paperen_NZ
dc.description.versionUnpublisheden_NZ
otago.bitstream.pages30en_NZ
otago.date.accession2011-02-01 23:18:17en_NZ
otago.schoolInformation Scienceen_NZ
otago.openaccessOpen
otago.place.publicationDunedin, New Zealanden_NZ
dc.identifier.eprints1088en_NZ
otago.school.eprintsInformation Scienceen_NZ
dc.description.references[1] T. Khanna, Foundations of Neural Networks, (1990) Addison-Wesley, New York. [2] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning Internal Representations by Error Propagation." chapter 8 in D. E. Rumelhart, J. L. McClelland, Parallel Distributed Processing, vol. 1, (1986), Cambridge, MA. [3] S. C. Shapiro (ed.), The Encyclopedia of Artificial Intelligence, vol 1, (1987) John Wiley & Sons, New York. [4] F. A. Jenkens and H. E. White, Fundamentals of Optics, (1976) McGraw-Hill, New York. [5] M. Born and E. Wolf, Principles of Optics, (1980) Pergamon, New York. [6] M. K. Purvis and Li X., "Connectionist Computations Based on an Optical Thin-Film Model", Proceedings of the First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, (1993) IEEE Computer Society Press, Los Alamitos, CA., pp. 130-433. [7] M. K. Purvis, and X. Li, "Connectionist Learning Using an Optical Thin-Fi1m Model", in Proceedings of the Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, (1995) IEEE Computer Society Press, Los Alamitos, CA., pp. 63-66. [8] J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation, Redwood City, CA (1991) Addison-Wesley Publishing Company, Reading, MA. [9] J. A. Dobrowolski, and R. A. Kemp, "Refinement of Optical Multilayer Systems with Different Optimization Procedures," Applied Optics, (1990) 29: 2876-2893. [10] W. E. Case, "New Synthesis Method for Optical Thin-Film Coatings," Applied Optics, (1983) 22(24): 4111-4117. [11] H. M. Liddell, Computer-aided Techniques for the Design of Multilayer Filters, (1981) Adam Hilger, Bristol. [12] H. A. MacLeod, W. E. Case, and M. K. Purvis, "Design of a Vanadium Dioxide Switchable Coating", in Topical Meeting on Optical Interference Coatings, Opt. Soc. of Am., 1984. [13] S. M. Weiss, and I. Kapouleus, "An Empirical Comparison of Pattern Recognition, Neural Nets and Machine Learning Classification Methods," Proceedings of the 11th International Joint Conference on Artificial Intelligence, (1989) Detroit, pp. 781-787. [14] B. D. Ripley, "Statistical Aspects of Neural Networks" in Networks and Chaos -- Statistical and Probabilistic Aspects, (1993) Chapman and Hall, London, pp. 40-123. [15] E. Anderson, "The Irises of the Gaspe Peninsula", Bulletin of the American Iris Society, (1935) vol 59 , pp. 2-5. [16] R. Fisher, "The Use of Multiple Measurements in Taxonomic Problems, Ann. Eugenics, (1936) 7:179-188. [17] L. Levi, Applied Optics, Vol II, (1980) John Wiley, New York. [18] E. W. Marchand, Gradient Index Optics, (1978) Academic Press, New York. [19] H. Fabricius, Applied Optics, 31:25 (1992), pp.5191-5196, 5216-5220. [20] A. Herpin, C. R. Acad. Sci, (1947) 225:182. [21] L. I. Epstein, J. Opt. Soc. Am, (1952) 42:806. [22] J. A. Dobrowolski and S. H. C. Piotrowski, " Refractive Index as a Variable in the Numerical DDesign of Optical Thin Film Systems", Applied Optics, (1982) 21:8, pp. 1502-1511. [23] R. Serra, and G. Zamarini, Complex Systems and Cognitive Processes, (1990) Springer-Verlag, New York.en_NZ
otago.relation.number96/14en_NZ
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record