Michael Revow

email: revow@cs.toronto.edu

Neural Network Research Group
Department of Computer Science
University of Toronto
6 Kings College Road
Canada M5S 3H5

Publications available online:

Using Mixtures of Factor Analyzers for Segmentation and Pose Estimation. Geoffrey E. Hinton and Michael Revow. Advances in Neural Information Processing Systems 9, MIT Press Cambridge MA abstract postscript (7 pages)

Honest assessments of automatic learning algorithm performance. Michael Revow and Daniel Maclean. Analytic and Quatitative Cytology and Histology 22(2), pp 123-132, 2000 abstract postscript (20 pages)

A comparison of statistical learning methods on the GUSTO database. Ennis M, Hinton G, Naylor D, Revow M, Tibshirani R. Statistics in Medicine 17 pp 2501-2508 1998.

Modeling the Manifolds of Images of Handwritten Digits. Geoffrey E. Hinton, Peter Dayan and Michael Revow. IEEE transactions on Neural Networks vol 8, 65-74 1997.abstract postscript (28 pages)

Using generative models for handwritten digit recognition. Michael Revow, Christopher K. I. Williams and Geoffrey E. Hinton. IEEE Transactions Pattern Analysis and Machine Intellegince 18(6), pp 592-606, 1996. abstract postscript (35 pages) software implementation README

Instantiating deformable models with a neural net. Christopher K. I. Williams, Michael Revow and Geoffrey E. Hinton. Computer Vision and Image Understanding 68(1) pp 120-126 1997. abstract postscript (16 pages)

Using Pairs of Data-Points to Define Splits for Decision Trees. Geoffrey E. Hinton and Michael Revow. In NIPS8, D. S. Touretzky, M. C. Mozer and M. E. Hasselmo MIT Press 1996. abstract postscript

Recognizing handwritten digits using mixtures of linear models. Geoffrey E. Hinton, Michael Revow and Peter Dayan. In NIPS7, G. Tesauro, D. S. Touretzky and T. K. Leen, eds 1995. abstract html postscript

Using mixtures of deformable models to capture variations in hand printed digits. Michael Revow, Christopher K. I. Williams and Geoffrey E. Hinton. Third International workshop on Frontiers in Handwriting Recognition, Buffalo, USA. pp 142-152, 1993. abstract postscript

Adaptive elastic models for hand-printed character recognition. Geoffrey E. Hinton, Christopher K. I. Williams and Michael Revow. In NIPS 4, J.E. Moody, S.J. Hanson and R.P Lippman (eds), 1992 postscript

Group Projects I have been involved with:

Mike Revow
Thu Aug 22 12:03:35 EDT 1996