The shape variational autoencoder: A deep generative model of
part-segmented 3D objectspdf
Charlie Nash, Christopher K.I. Williams. Accepted version of the
paper to appear in Computer Graphics Forum 36(5) (2017) 1-12, presented at the
Symposium on Geometry Processing, July 2017.
Sohan Seth, Ahsan R. Akram, Kevin Dhaliwal, Christopher
K.I. Williams. Accepted for publication at
Medical Image Understanding and Analysis (MIUA) 2017.
Pol Moreno, Christopher K.I. Williams, Charlie Nash and
Pushmeet Kohli. Presented at:
Geometry Meets Deep Learning workshop, ECCV 2016 (oral presentation).
Final m/s version of paper appearing in Computer Vision-ECCV 2016 Workshops Proceedings Part
III, eds. H. Gang and H. Jegou,
Springer LNCS
9915 pp 170-185. Code
is available.
Input-Output Non-Linear Dynamical Systems applied to
Physiological Condition Monitoringpdf
Konstantinos Georgatzis, Christopher K.I. Williams and
Christopher Hawthorne. Proc
Machine Learning in Health Care,
JMLR W&C Track Volume 56, 2016.
Assessing the utility of autofluorescence-based pulmonary
optical endomicroscopy to predict the malignant potential of solitary
pulmonary nodules in humanspdf
Sohan Seth, Ahsan R. Akram, Paul McCool, Jody Westerfeld,
David Wilson, Stephen McLaughlin, Kevin Dhaliwal, Christopher
K. I. Williams. Scientific Reports
6:31372 (2016). doi: 10.1038/srep31372
Detecting Artifactual Events in Vital Signs Monitoring Data pdf
Partha Lal, Christopher K. I. Williams, Konstantinos Georgatzis,
Christopher Hawthorne, Paul McMonagle, Ian Piper, Martin Shaw.
Technical report, October 2015.
Associated
software.
A slightly revised version is published as a chapter in
Machine Learning for Healthcare Technologies,
ed. David A. Clifton,
Institution of Engineering and Technology, 2016.
Tree-Cut for Probabilistic Image Segmentation
Shell X. Hu, Christopher K. I. Williams, Sinisa Todorovic.
Posted on arXiv 11 June 2015
(pdf).
Discriminative Switching Linear Dynamical Systems applied to
Physiological Condition Monitoringpdf
Konstantinos Georgatzis, Christopher K. I. Williams.
In Proc UAI 2015.
An earlier version was posted on arXiv 24 April 2015
(pdf).
2014
Localisation microscopy with quantum dots using non-negative matrix
factorisationpdf
Ondrej Mandula, Ivana Sumanovac Sestak, Rainer
Heintzmann, Christopher K. I. Williams
Optics Express, Vol. 22, Issue 20, pp. 24594-24605 (2014),
http://dx.doi.org/10.1364/OE.22.024594.
Software developed for this project is
available.
A Hierarchical Switching Linear Dynamical System Applied to the
Detection of Sepsis in Neonatal Condition Monitoringpdf
Ioan Stanculescu, Christopher K. I. Williams, Yvonne Freer
In Proceedings of the 30th Conference on Uncertainty in
Artificial Intelligence (UAI 2014).
The PASCAL Visual Object Classes Challenge - a Retrospectivepdf
Mark Everingham, S. M. Ali Eslami, Luc Van Gool,
Christopher K. I. Williams, John Winn, Andrew Zisserman.
Accepted for publication in International Journal of Computer
Vision on 20 May 2014. Published: International Journal of Computer Vision
111(1), pp 98-136, 2015.
The final publication is available
at http://link.springer.com,
DOI 10.1007/s11263-014-0733-5
Visual Boundary Prediction: A Deep Neural Prediction Network
and Quality Dissectionpdf,
supplementary material
Jyri J. Kivinen, Christopher K. I. Williams, Nicolas Heess
In Proceedings of the 17th International Conference on
Artificial Intelligence and Statistics (AISTATS)
2014, Reykjavik, Iceland. JMLR: W&CP volume 33.
2013
Dictionary of Computer Vision and Image Processing (second edition)
website
Robert B. Fisher, Toby Breckon, Kenneth Dawson-Howe, Andrew
Fitzgibbon, Craig Robertson, Emanuele Trucco, Christopher
K. I. Williams.
Wiley, 2014, ISBN: 978-1-119-94186-6.
Autoregressive Hidden Markov Models for the Early Detection of
Neonatal Sepsispreprint pdf
Ioan Stanculescu, Christopher K.I. Williams, and Yvonne Freer
Accepted for publication in
IEEE Journal of Biomedical and Health Informatics on 1 Dec 2013.
Published in J-BHI 18(5) 1560-1570, September 2014.
The Shape Boltzmann Machine: a Strong Model of Object Shapepreprint pdf
S. M. Ali Eslami, Nicolas Heess, Christopher K. I. Williams, John
Winn Int Journal of Computer Vision, doi
10.1007/s11263-013-0669-1 (Nov 2013). The final publication is
available
at http://link.springer.com as
Int Journal of Computer Vision, 107(2) 155-176 (2014)
Assessing the Significance of Performance Differences on the
PASCAL VOC Challenges via Bootstrappingpdf
Mark Everingham, S. M. Ali Eslami, Luc Van Gool,
Christopher K. I. Williams, John Winn, Andrew Zisserman
Technical note, October 2013.
A Framework for Evaluating Approximation Methods for Gaussian
Process Regression
Krzysztof Chalupka, Christopher K. I. Williams, Iain Murray v2 posted on arXiv, 5 Nov
2012.
Accepted for publication in Journal of Machine Learning Research 17
Dec 2012, published in vol 14 pp 333-350 (2013)
JMLR pdf.
link
to code and data.
Grigori Fursin, Yuriy Kashnikov, Abdul Wahid Memon, Zbigniew Chamski,
Olivier Temam, Mircea Namolaru, Elad Yom-Tov, Bilha Mendelson, Ayal
Zaks, Eric Courtois, Francois Bodin, Phil Barnard, Elton Ashton, Edwin
Bonilla, John Thomson, Christopher K. I. Williams, Michael O'Boyle.
International Journal of Parallel Programming
39(3) pp 296-327 (2011)
DOI:10.1007/s10766-010-0161-2
Physiological Monitoring with
Factorial Switching Linear Dynamical Systemspdf
J.A. Quinn and C.K.I. Williams.
Chapter appearing in
Bayesian Time Series Models, eds. D. Barber,
A. T. Cemgil, S. Chiappa, Cambridge University Press, 2011.
S. Harmeling and C. K. I. Williams
Final manuscript version of the paper accepted to appear in
IEEE PAMI.
Published in IEEE Transactions on Pattern Analysis and Machine
Intelligence 33(6) 1087-1097 (2011). Matlab
code is available.
The PASCAL Visual Object Classes (VOC) Challengepdf
M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn,
A. Zisserman
Final manuscript version of the paper in
International Journal
of Computer Vision 88(2), 303-338 (2010)
Multi-task Gaussian Process Learning of Robot Inverse
Dynamicspdf
K. M. A. Chai, C. K. I. Williams, S. Klanke, S. Vijayakumar
In Advances in Neural Information Processing Systems
21, eds D. Koller, Y. Bengio, D. Schuurmans, L. Bottou (2009)
D.J. MacGregor, C.K.I. Williams, G. Leng.
Journal of Neuroscience Methods, 176(1) 2009, Pages 45-56,
doi:10.1016/j.jneumeth.2008.08.011
2008
Factorial Switching Linear Dynamical Systems applied to
Physiological Condition Monitoringpdf
John A. Quinn, Christopher K.I. Williams, Neil McIntosh.
Accepted to IEEE Trans. on Pattern Analysis and Machine Intelligence
(July 2008), published T-PAMI 31(9) pp 1537-1551 (2009).
Matlab
code is available.
MILEPOST GCC: machine learning based research compilerpdf
G. Fursin, C. Miranda. O. Teman et al [including C. K. I. Williams],
Proceedings of the GCC Developers' Summit, 2008
Edwin V. Bonilla, Kian Ming A. Chai,
Christopher K. I. Williams.
In Advances in Neural Information Processing Systems
20, eds. J. C. Platt, D. Koller, Y. Singer, S. Roweis, MIT Press
(2008) NB See this correction
note concerning the results reported in section 6 (Jan 2009)
2007
EDI-INF-RR-1228A Note on Noise-free Gaussian Process Prediction with Separable
Covariance Functions and Grid Designspdf
Christopher K. I. Williams, Kian Ming A. Chai, Edwin V. Bonilla
Informatics Research Report, December 2007.
Approximation Methods for Gaussian Process Regressionpdf
Joaquin Quinonero-Candela, Carl Edward Rasmussen,
Christopher K. I. Williams.
Final draft of a chapter in
Large Scale Kernel Machines
eds. L. Bottou, O. Chapelle, D. DeCoste, J. Weston, pages 203-223
MIT Press, 2007
Known Unknowns: Novelty Detection in Condition Monitoringpdf
John A. Quinn, Christopher K. I. Williams.
Invited paper in Proc 3rd
Iberian Conference on Pattern Recognition and Image Analysis
(IbPRIA 2007),
eds J. Marti, J. M. Benedi, A. M. Mendonca,
J. Serrat, LNCS 4477
pp 1-6, Springer-Verlag
Kernel Multi-task Learning using Task-specific Featurespdf
Edwin V. Bonilla, Felix V. Agakov, Christopher K. I. Williams.
Proc AISTATS 2007.
2006
On the Extension of Eigenvectors to New Datapointspdf
C. K. I. Williams.
Technical note, November 2006.
Sequential Learning of Layered Models from Videopdf
M. K. Titsias, C. K. I. Williams.
In Toward Category-Level Object Recognition,
eds. J. Ponce, M. Hebert, C. Schmid, and A. Zisserman,
LNCS 4170,
Springer-Verlag, pp 577-595, 2006.
J. Ponce, T.L. Berg,
M.R. Everingham, D.A. Forsyth, M. Hebert, S. Lazebnik, M. Marszalek,
C. Schmid, B.C. Russell, A. Torralba, C.K.I. Williams, J. Zhang, and
A. Zisserman. In Toward Category-Level Object Recognition,
eds. J. Ponce, M. Hebert, C. Schmid, and A. Zisserman,
LNCS 4170,
Springer-Verlag, pp 29-48 2006.
The PASCAL Visual Object Classes Challenge 2006 (VOC 2006) Resultspdf
Mark Everingham, Andrew Zisserman, Chris Williams, Luc Van Gool
Technical Report, September 2006.
Edwin V. Bonilla, Christopher K. I. Williams, Felix V. Agakov,
John Cavazos, John Thomson, Michael F.P. O'Boyle
In Proc. ICML 2006
Using Machine Learning to Focus Iterative Optimizationpdf
F. Agakov, E. Bonilla, J. Cavazos, B. Franke, G. Fusin,
M. F. P. O'Boyle, J. Thomson, M. Toussaint, C. K. I. Williams.
The 4th Annual International Symposium on Code Generation and
Optimization (CGO), March 2006.
Factorial Switching Kalman Filters for Condition Monitoring in
Neonatal Intensive Carepdf
Christopher K. I. Williams, John Quinn, Neil McIntosh
To appear in Advances in Neural Information Processing Systems
18, eds. Y. Weiss, B. Schoelkopf, J. C. Platt, MIT Press (2006)
2005
Unsupervised Learning of Multiple Aspects of Moving Objects from Video
pdf
The 2005 PASCAL Visual Object Classes Challengepdf
M. Everingham, A. Zisserman, C. K. I. Williams, L. Van Gool, et al.
In Machine Learning Challenges, eds.
J. Quinonero-Candela, I. Dagan, B. Magnini, F. d'Alche-Buc,
LNAI 3944, Springer-Verlag, 2006.
EDI-INF-RR-0318An Expectation Maximisation Algorithm for One-to-Many Record Linkage, Illustrated on the Problem of Matching Far Infra-Red Astronomical Sources to Optical Counterparts
A. J. Storkey, C. K. I. Williams, E. Taylor, R. G. Mann
Informatics Research Report, August 2005.
Understanding Gaussian Process Regression Using the Equivalent
Kernelpdf
Max Welling, Felix V. Agakov, Christopher K. I. Williams Advances in Neural Information
Processing Systems 16 eds. S. Thrun, L. Saul, B. Schoelkopf,
MIT Press (2004).
2003
EDI-INF-RR-0185An isotropic Gaussian mixture can have more modes than components
Miguel A. Carreira-Perpinan, Christopher K. I. Williams
Informatics Research Report, December 2003.
See
Miguel's
webpage for some animations relating to these results.
Storkey A.J., N.C. Hambly, C.K.I. Williams, R.G. Mann
In Uncertainty in Artificial Intelligence: Proceedings of the
Nineteenth Conference (UAI-2003), 559-566.
Miguel A. Carreira-Perpinan, Christopher K. I. Williams
Informatics Research Report, February 2003.
A slightly shortened version appears in Scale Space '03
(Proceedings of the 4th International Conference on Scale Space
Theories in Computer Vision, June 2003). Note (Dec 03): The conjecture given in this paper
that if the components of the mixture have the same covariance matrix
then the number
of modes cannot exceed the number of components
is false. See
EDI-INF-RR-0185 for details.
Learning About Multiple Objects in Images:
Factorial Learning without Factorial Searchgzipped postscript
Christopher K. I. Williams, Michalis K. Titsias Advances in Neural Information
Processing Systems 15 eds. S. Becker, S. Thrun, K. Obermayer
MIT Press (2003)
The Stability of Kernel Principal Components Analysis and its
Relation to the Process Eigenspectrumgzipped postscript
John Shawe-Taylor, Christopher K. I. Williams Advances in Neural Information
Processing Systems 15 eds. S. Becker, S. Thrun, K. Obermayer
MIT Press (2003)
A longer version of this paper (with author list
John Shawe-Taylor, Chris Williams, Nello Cristianini, and Jaz Kandola)
also appeared in the Proceedings of the
5th International Conference on Discovery Science, eds
Steffen Lange, Ken Satoh, and Carl H. Smith,
Lecture Notes in Computer Science vol 2534, Springer-Verlag (2002).
2002
UKeS-2002-06Scientific Data Mining, Integration and Visualisation
Bob Mann, Roy Williams, Malcolm Atkinson, Ken Brodlie, Amos Storkey,
Chris Williams.
Final Report of the meeting on Scientific Data Mining, Integration and
Visualisation held at the eScience Institute, Edinburgh, 24-25 October 2002.
Image modelling with position-encoding dynamic treespdf
Amos J. Storkey, Christopher K. I. Williams.
Final draft of paper appearing in IEEE Pattern Analysis and Machine
Intelligence 25(7) 859-871 (2003). IEEE legal stuff
This material is presented to ensure
timely dissemination of scholarly and technical work. Copyright
and all rights therein are retained by authors or by other
copyright holders. All persons
copying this information are expected to adhere to the terms and
constraints invoked by each author's copyright. In most cases, these
works may not be reposted without explicit permission of the copyright
holder.
Fast Forward Selection to Speed Up Sparse Gaussian Process
Regression
gzipped postscript
Matthias Seeger, Christopher K.I. Williams and Neil Lawrence. AI-STATS 2003
Observations on the Nystroem Method for Gaussian Process Predictiongzipped postscript
Christopher K. I. Williams, Carl Edward Rasmussen, Anton Schwaighofer,
Volker Tresp.
An Analysis of Contrastive Divergence Learning in Gaussian
Boltzmann Machinespdf
Christopher K. I. Williams and Felix V. Agakov
Informatics Research Report EDI-INF-RR-0120, May 2002.
Christopher K. I. Williams, Felix V. Agakov, Stephen N.
Felderof Advances in Neural Information
Processing Systems 14 eds. T. G. Diettrich, S. Becker, Z. Ghahramani
MIT Press (2002)
2001
Products of Gaussians and Probabilistic Minor Component Analysisgzipped postscript
C. K. I. Williams and F. V. Agakov
Informatics Research Report EDI-INF-RR-0043, July 2001.
A shortened version of this
report has been published in Neural Computation,
14(5), 1169-1182 (2002).
Comparing Mean Field and Exact EM in Tree Structured Belief Networksgzipped postscript
Nicholas J. Adams, Christopher K. I. Williams and Amos J. Storkey
In Proceedings of Fourth International ICSC Symposium on Soft Computing and
Intelligent Systems for Industry, June 2001.
Products and Sums of Tree-Structured Gaussian Processesgzipped postscript
Christopher K. I. Williams and Stephen N. Felderhof
In Proceedings of Fourth International ICSC Symposium on Soft Computing and
Intelligent Systems for Industry, June 2001.
Francesco Vivarelli and Christopher K. I. Williams
Technical report, July 2001. This TR is a close-to-final draft of
a paper which was published in Neural Networks 14(4-5)
May 2001, 427-437.
Combining belief networks and neural networks for scene segmentationgzipped postscript
Xiaojuan Feng, C. K. I. Williams and S. N. Felderhof
Submitted to IEEE Trans PAMI, April 1999. Revised version March 2001,
accepted for publication July 2001. Published in IEEE Trans PAMI
24(4) 467-483 (2002) IEEE legal stuff
This material is presented to ensure
timely dissemination of scholarly and technical work. Copyright
and all rights therein are retained by authors or by other
copyright holders. All persons
copying this information are expected to adhere to the terms and
constraints invoked by each author's copyright. In most cases, these
works may not be reposted without explicit permission of the copyright
holder. Software developed for this project is
available.
Christopher K. I. Williams and Matthias Seeger Advances in Neural Information
Processing Systems 13 eds. T. K. Leen, T. G. Diettrich, V. Tresp.
MIT Press (2001)
The version above is final, replaces version as submitted to NIPS which
was posted on this page 18 June 2000 NB See the later paper
"Observations on the Nystroem Method for Gaussian Process Prediction" by
Christopher K. I. Williams, Carl Edward Rasmussen, Anton
Schwaighofer, Volker Tresp (2002) [available above] for
important additional comments on the Nystroem method.
On a Connection between Kernel PCA and Metric Multidimensional
Scalinggzipped postscript
Christopher K. I. Williams Advances in Neural Information
Processing Systems 13 eds. T. K. Leen, T. G. Diettrich, V. Tresp.
MIT Press (2001)
Dynamic Positional Trees for Structural Image Analysisgzipped postscript
Amos J. Storkey and Christopher K. I. Williams
In: Proceedings of the Eighth International Workshop on
Artificial Intelligence and Statistics (2001)
2000
The Effect of the Input Density Distribution on Kernel-based
Classifiersgzipped postscript
Christopher K. I. Williams and Matthias Seeger
In: Proceedings of the Seventeenth
International Conference on Machine Learning. Morgan
Kaufmann (2000).
Nicholas J. Adams, Amos J. Storkey, Zoubin Ghahramani and
Christopher K. I. Williams
In: Proceedings of 15th International Conference on
Pattern Recognition, 2000.
Nicholas J. Adams and C. K. I. Williams
In ICANN 99: Artificial Neural Networks
Finite-dimensional approximation of Gaussian processesgzipped postscript
Giancarlo Ferrari Trecate and C. K. I. Williams and M. Opper
In: Advances in Neural Information Processing Systems 11,
eds. M. J. Kearns, S. A. Solla and D. A. Cohn. MIT Press, 1999.
Discovering hidden features with Gaussian processes regressiongzipped postscript
Francesco Vivarelli and C. K. I. Williams
In: Advances in Neural Information Processing Systems 11,
eds. M. J. Kearns, S. A. Solla and D. A. Cohn. MIT Press, 1999.
C. K. I. Williams and Nicholas J. Adams
In: Advances in Neural Information Processing Systems 11,
eds. M. J. Kearns, S. A. Solla and D. A. Cohn. MIT Press, 1999.
1998
NCRG/98/002Regression with Input-dependent Noise: A Gaussian Process Treatment
P. W. Goldberg and C. K. I. Williams and C. M. Bishop In Advances in Neural Information Processing Systems 10.
Editor: M. I. Jordan and M. J. Kearns and S. A. Solla. MIT Press.
NCRG/98/012Developments of the Generative Topographic Mapping
C. M. Bishop and M. Svensen and C. K. I. Williams In
Neurocomputing 21 203-224 (1998).
NCRG/98/013Combining neural networks and belief networks for image segmentation
C. K. I. Williams and X. Feng In Proc. 1998 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing.
Cambridge, UK, 31 August-3 September 1998.
NCRG/98/014Training Bayesian networks for image segmentation
X. Feng and C. K. I. Williams In Proceedings of SPIE vol 3457.
Presented at SPIE's 43rd Annual Meeting, San Diego, CA, July 19-24
1998.
NCRG/98/015Upper and lower bounds on the learning curve for Gaussian processes
Revised version of 24 April 1999 available as
gzipped postscipt.
Christopher K. I. Williams and Francesco Vivarelli
Final version appears in Machine Learning,
40(1), 77-102 (2000)
NCRG/98/023Bayesian Inference for Wind Field Retrieval
Dan Cornford and Ian T. Nabney and Christopher K. I. Williams
Neurocomputing , 30(1-4), 3-11, 1999.
NCRG/98/025Adding Constrained Discontinuities to Gaussian Process Models of
Wind Fields
Dan Cornford and Ian T. Nabney and Christopher
K. I. Williams Advances in Neural Information
Processing Systems 11, eds. M. J. Kearns, S. A. Solla and
D. A. Cohn.
C. K. I. Williams and David Barber In: IEEE Trans Pattern
Analysis and Machine Intelligence , 20(12) 1342-1351,
(1998). IEEE legal stuff: This material is presented to ensure
timely dissemination of scholarly and technical work. Copyright
and all rights therein are retained by authors or by other
copyright holders. All persons
copying this information are expected to adhere to the terms and
constraints invoked by each author's copyright. In most cases, these
works may not be reposted without explicit permission of the copyright
holder.
Code is available.
1997
NCRG/97/006Magnification Factors for the GTM Algorithm
Christopher M. Bishop and Markus Svensen and Christopher K. I. Williams In Proceedings IEE Fifth International Conference on Artificial Neural Networks.
NCRG/97/007Using Bayesian neural networks to classify segmented images
Francesco Vivarelli and Christopher K. I. Williams In Proceedings of the IEE fifth International Conference on Artificial Neural Network s.
NCRG/97/008Magnification Factors for the SOM and GTM Algorithms
Christopher M. Bishop, Markus Svensen and Christopher K. I. Williams In Proceedings 1997 Workshop on Self-Organizing Maps, Helsinki, Finland.
NCRG/97/011Gaussian Regression and Optimal Finite Dimensional Linear
Models
Huaiyu Zhu and Christopher K. I. Williams and Richard Rohwer and
Michal Morciniec Aston University.
Also appears in C.
M. Bishop (editor), Neural Networks and Machine
Learning, 1998, Springer-Verlag,
NCRG/97/012Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond
C. K. I. Williams Aston University, UK. In "Learning and
Inference in Graphical Models", ed. M. I. Jordan, Kluwer, 1998.
NCRG/97/015Bayesian Classification with Gaussian Processes
Christopher K. I. Williams and David Barber Neural Computing
Research Group, Aston University. Submitted to IEEE PAMI, 16 November
1997.
NCRG/97/025Computation with infinite neural networks
Christopher K. I. Williams
Neural Computing Research Group, Aston University. Similar to
paper published in Neural Computation 10(5), pp 1203-1216, (1998).
1996
NCRG/96/005An Upper Bound on the Bayesian Error Bars for Generalized Linear Regression
Cazhaow S. Qazaz and Christopher K. I. Williams and Christopher
M. Bishop . In Mathematics of Neural Networks: Models,
Algorithms and Applications. Eds. S. W. Ellacott, J. C. Mason,
I. J. Anderson. Kluwer, 1977.
NCRG/96/011EM Optimization of Latent-Variable Density Models
Christopher M. Bishop and M. Svensen and Christopher K. I. Williams In Advances in Neural Information Processing Systems.
Editor: D. S. Touretzky and M. C. Mozer and M. E. Hasselmo.
8. MIT Press, Cambridge, MA.
C. K. I. Williams and C. E. Rasmussen In Advances in Neural Information Processing Systems 8.
Editor: D. S. Touretzky and M. C. Mozer and M. E. Hasselmo.
MIT Press.
NCRG/96/015GTM: The Generative Topographic Mapping
Christopher M. Bishop and Markus Svensen and Christopher
K. I. Williams Neural Computation 10(1), 215-234
(1998).
Associated software: GTM
toolbox
misc96-007Using generative models for handwritten digit recognition
Revow, M. and Williams, C. K. I. and Hinton, G. E. IEEE Transactions on Pattern Analysis and Machine Intelligence .
18(6). pp 592-606.
Code is available from
Michael Revow's homepage.
NCRG/96/025Instantiating deformable models with a neural net
C. K. I. Williams and M. Revow and G. E. Hinton Computer Vision
and Image Understanding 68(1) 120-126 (1997).
C. K. I. Williams In Advances in Neural Information Processing Systems 9.
Editor: M. C. Mozer and M. I. Jordan and T. Petsche.
MIT Press, Cambridge, MA.
NCRG/96/027Gaussian Processes for Bayesian Classification via Hybrid Monte Carlo
D. Barber and C. K. I. Williams In Advances in Neural Information Processing Systems 9.
Editor: M. C. Mozer and M. I. Jordan and T. Petsche.
MIT Press, Cambridge, MA.
NCRG/96/030GTM: A Principled Alternative to the Self-Organizing Map
Christopher M. Bishop, Markus Svensen and Christopher
K. I. Williams In
Advances in Neural Information Processing Systems 9. Eds
M. C. Mozer, M. I. Jordan and T. Petsche. MIT Press.
NCRG/96/031GTM: A Principled Alternative to the Self-Organizing Map
Christopher M. Bishop and M. Svensen and Christopher K. I. Williams In Proceedings 1996 International Conference on Artificial Neural Networks, ICANN'96.
Editor: C. von der Malsburg and W. von Seelen and J. C. Vorbruggen and B. Sendhoff.
pp 164--170. Springer-Verlag.
C. K. I. Williams Paper presented at the Mathematics of Neural
Networks and Applications conference, Oxford, UK, July 1995. In
Mathematics of Neural Networks: Models, Algorithms and
Applications. Eds. S W Ellacott, J C Mason and I J Anderson,
Kluwer, 1997.
NCRG/95/024On the relationship between Bayesian error bars and the input data density
C. K. I. Williams and C. Qazaz and C. M. Bishop and H. Zhu In Proc. Fourth International Conference on Artificial Neural Networks.
Richard S. Zemel, C. K. I. Williams, and Michael Mozer.
Neural Networks, 8(4), pp. 503-512 (1995).
1994
Combining deformable models and neural networks for
handprinted digit recognition
compressed postscript
C. K. I. Williams PhD thesis. Department of Computer Science,
University of Toronto.
1993
Using mixtures of deformable models to capture variations in hand
printed digitsgzipped postscript
Michael Revow, Christopher K. I. Williams and Geoffrey E. Hinton
In: Third International workshop on Frontiers in Handwriting Recognition, Buffalo, USA. pp 142-152.
1992
Adaptive elastic models for hand-printed character recognition gzipped postscript
Geoffrey E. Hinton, Christopher K. I. Williams and Michael Revow
In Advances in Neural Information Processing 4,
J.E. Moody, S.J. Hanson and R.P Lippman (eds), Morgan Kaufmann, 1992
Learning to Segment Images Using Dynamic Feature Bindingpdf
Michael C. Mozer, Richard S. Zemel, Marlene Behrmann,
Christopher K. I. Williams
In Neural Computation 4 650-665 (1992).
1990
Mean field networks that learn to discriminate teporally distorted stringspdf
Christopher K. I. Williams and Geoffrey E. Hinton
In: Proceedings of the 1990 Connmectionist Models Summer School, eds
D. S. Touretzky, J. L. Elman, T. J. Sejnowski, G. E. Hinton.
Morgan Kaufmann (1990).