%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 07:01:54 PM

@INPROCEEDINGS{Saxena-97.3,
         author = {Saxena, Indu and Moerland, Perry and Fiesler, Emile and Pourzand, A. R.},
         editor = {Gerstner, W. and Germond, A. and Hasler, M. and Nicoud, J. -D.},
       projects = {Idiap},
          title = {Handwritten Digit Recognition with Binary Optical Perceptron},
      booktitle = {Proceedings of the International Conference on Artificial Neural Networks (ICANN'97)},
         series = {Lecture Notes in Computer Science},
         number = {1327},
           year = {1997},
      publisher = {Springer-Verlag},
        address = {Berlin},
           note = {IDIAP-RR 97-15},
       crossref = {saxena-97.4},
       abstract = {Binary weights are favored in electronic and optical hardware implementations of neural networks as they lead to improved system speeds. Optical neural networks based on fast ferroelectric liquid crystal binary level devices can benefit from the many orders of magnitudes improved liquid crystal response times. An optimized learning algorithm for all-positive perceptrons is simulated on a limited data set of hand-written digits and the resultant network implemented optically. First, gray-scale and then binary inputs and weights are used in recall mode. On comparing the results for the example data set, the binarized inputs and weights network shows almost no loss in performance.},
            pdf = {https://publications.idiap.ch/attachments/reports/1997/rr97-15.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/1997/rr97-15.ps.gz},
ipdmembership={learning},
}



crossreferenced publications: 
@TECHREPORT{Saxena-97.4,
         author = {Saxena, Indu and Moerland, Perry and Fiesler, Emile and Pourzand, A. R.},
       projects = {Idiap},
          title = {Handwritten Digit Recognition with Binary Optical Perceptron},
           type = {Idiap-RR},
         number = {Idiap-RR-15-1997},
           year = {1997},
    institution = {IDIAP},
           note = {Published in ``Proceedings of the International Conference on Artificial Neural Networks (ICANN'97)''},
       abstract = {Binary weights are favored in electronic and optical hardware implementations of neural networks as they lead to improved system speeds. Optical neural networks based on fast ferroelectric liquid crystal binary level devices can benefit from the many orders of magnitudes improved liquid crystal response times. An optimized learning algorithm for all-positive perceptrons is simulated on a limited data set of hand-written digits and the resultant network implemented optically. First, gray-scale and then binary inputs and weights are used in recall mode. On comparing the results for the example data set, the binarized inputs and weights network shows almost no loss in performance.},
            pdf = {https://publications.idiap.ch/attachments/reports/1997/rr97-15.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/1997/rr97-15.ps.gz},
ipdmembership={learning},
}