- Homotopy Approaches for the Analysis and Solution of Neural Network and
Other Nonlinear Systems of Equations.
- Frans M. Coetzee , "Correcting the Kullback-Leibler Distance for Feature
Selection",Pattern Recognition Letters Volume 26 (11), August 2005, 1675–1683
- Flake, G. W., Lawrence, S., Giles, C. L. & Coetzee, F.
"Self-organization and identification of communities". IEEE Computer 35, 66
- 71 (2002)
- Steve Lawrence, Frans Coetzee, Eric Glover, David Pennock, Gary Flake,
Finn Nielsen, Robert Krovetz, Andries Kruger and C. Lee Giles, "Persistence
of Web References in Scientific Research”,IEEE Computer, 34 (2), pp 26—3,
- Coetzee F.M. and Elghazzawi, L. “Noise resistant pulse oximetry using a
synthetic reference”, IEEE Transactions on Biomedical Engineering , Vol 47
(8), pp1027-1035, August 2000.
- Coetzee F.M. and Stonick V.L. “On finding multiple solutions using
repeated trials”, Journal of Global Optimization, Vol 13, pp. 241-254, 1998
- Coetzee F.M. and Stonick V.L. “On a natural homotopy between linear and
nonlinear single layer perceptron networks”, IEEE Transactions on Neural
Networks, Vol. 7(2), pp. 307-317, March 1996.
- Coetzee F.M. and Stonick V.L. “On the uniqueness of weights in single
layer perceptrons”, IEEE Transactions on Neural Networks, Vol. 7(2), pp.
318-325, March 1996.
- Coetzee F.M. and Stonick V.L. “Topology and geometry of single hidden
layer networks, least squares weight solutions”, Neural Computation, 7(4),
pp. 672-705, July 1995.
- Coetzee F.M. and Swart P.L. “A hybrid system for digital image data
compression”, Transactions of the SAIEE, pp. 66-71, March 1990.
General Interest Pieces
- Frans M. Coetzee , "Here Be Dragons: Managing a Tech Startup". This was a six-part print/online series
in IEEE Spectrum that I wrote following my startup experiences with Certus and GenuOne.
- Rule 1 in managing a technology start-up: beware the easy money (9/2004)
- A VC, a Board and a Lawyer (10/2004)
- The Startup CEO and CTO (11/2004)
- Hiring Staff and Other Annoyances (1/2005)
- The Battle Over Product Development (2/2005)
- The Company You Keep (4/2005)
- Frans M. Coetzee and Ramesh Visvanathan, "Semi-Automatic Probabilistic
Morphological Detection", Proc. IEEE International Conference on Acoustic, Speech and Signal Processing
(ICASSP 2005) Philadelphia PA, March 2005
- B. Stenger, V. Ramesh, N. Paragios, F. Coetzee and J. Buhman "Topology
Free Hidden Markov Models: Application to Background Modeling", IEEE
International Conference in Computer Vision [ICCV] , Vancouver Canada, July
- Frans Coetzee, Eric Glover, Steve Lawrence, C. Lee Giles , “Feature
Selection in Web Applications by ROC Inflections and Powerset Pruning”,
Symposium on Applications and the Internet, SAINT 2001, San Diego, January
- Frans Coetzee, Steve Lawrence and C. Lee Giles, "Bayesian Classification
and Feature Selection from Finite Data Sets", Sixteenth Conference on
Uncertainty in Artificial Intelligence (UAI-2000)", Stanford, CA, June
30--July 3, pp 89--97, 2000
- Andries Kruger, C. Lee Giles, Frans Coetzee, Eric Glover, Gary Flake,
Steve Lawrence, and Cristian Omlin. “DEADLINER: Building a new niche search
engine”. In Ninth International Conference on Information and Knowledge
Management, CIKM 2000, Washington, DC, November 6-- 11 2000.
- Michelangelo Diligenti, Frans Coetzee, Steve Lawrence, C. Lee Giles, and
Marco Gori. “Focused crawling using context graphs”. In 26th International
Conference on Very Large Databases, VLDB 2000, Cairo, Egypt, 10--14
- Xiang Gao, T.E.Boult, Frans Coetzee, Visvanathan Ramesh, "Error Analysis
of Background Adaption", IEEE Computer Society Conference on Computer Vision
and Pattern Recognition, pp503-510, Hilton Head Island, South Carolina, June
- Rao B.R., Rickard S. and Coetzee F.M. “Time series forecasting from
high-dimensional data with multiple adaptive layers”, Proc. AAAI 4th
International Conference on Knowledge Discovery and Data Mining, Aug 1998.
- Coetzee F.M. and Stonick V.L. “488 Solutions to the XOR Problem”,
Advances in Neural Information Processing Systems 1996 (NIPS '96), Denver
CO, December 1996.
- Coetzee F.M. and Stonick V.L. “Sequential homotopy-based computation of
multiple solutions to nonlinear equations”, Proc. IEEE International
Conference on Acoustics, Speech and Signal Processing, Detroit, MI, May
- Coetzee F.M. and Stonick V.L. “Bifurcations in nonlinear networks
initialized with linear network weight solutions”, Proc. IEEE International
Conference on Neural Networks, pp. 453-458, Orlando, FL, June1994.
- Coetzee F.M. and Stonick V.L. “A geometric view of neural networks using
homotopy”, Proc. 1993 IEEE Workshop on Neural Networks for Signal
Processing, pp. 118-127, Linthicum Heights MD, September 1993.
- Coetzee F.M. and Stonick V.L. “Improving neural network performance by
adapting node nonlinearities”, Proc. SPIE, Vol. 1766, pp. 212-223, San Diego
CA, July 1992.
- Coetzee F.M. and Casasent D.P. “Focusing and collimating laser diodes
and laser diode arrays”, Proc. SPIE, Vol. 1544, pp. 108-122, San Diego CA,
- Casasent D.P., Coetzee F.M., Natarajan S., Xu T. and Yu D. “Accuracy of
CGH encoding schemes for optical data processing”, Proc. SPIE, Vol. 1555,
pp. 23-33, San Diego CA, July 1991.
- Carender N., Casasent D.P., Coetzee F.M. and Yu D. “Hough transform
computer generated holograms: new output format”, Proc. SPIE, Vol. 1555, pp.
182-193, San Diego CA, July 1991.
- Casasent D.P and Coetzee F.M. “Error diffusion multilevel phase encoded
CGH elements”, Proc. SPIE, Vol 1347, pp. 78-85, San Diego CA, July 1990.
Invited Presentations and Workshops
- F. M. Coetzee “When the Kullback-Leibler Distance Yields Sub-Optimal Features", Snowbird Machine Learning Conference (Utah), April 2003
- G. Towell, J. Saponara, J. O’Ruanaidh, F. M. Coetzee,
“Finding internet piracy", Snowbird Machine Learning Conference (Utah), April 2003.
- F. M. Coetzee, Steve Lawrence and C. L. Giles “Possible Directions for Feature Selection from Finite Data Sets",
Snowbird Machine Learning Conference, April 2000
- F. M. Coetzee, “Dealing with Deja-Vu: Linear and Nonlinear Filtering of Almost-Periodic
Signals”, NEC Research Institute, July 1999.
- F. M. Coetzee “Adaptive filtering using restricted subspaces”, Applied Mathematics
Time-Frequency Seminar, Princeton University, April 1998.
- F. M. Coetzee and V. L. Stonick “Geometric and Topological Investigations of Neural Network Error
Surfaces”, in Modeling Error Surfaces, Neural Information Processing
Workshops 1996 (NIPS '96), Snowmass CO, December 1996.
Patents and Disclosures
- Coetzee F.M., “Adaptive filtering of physiological signals using a
modeled synthetic reference signal”, US PAT 6,135,952, issued 8/2000
- Coetzee F.M., "Method and apparatus for adaptively reducing the level of
noise in an acquired signal", US PAT 5,924,980 issued 4/99
- N. Paragios, Visvanathan R., Stenger B. Coetzee F.M, "Real-time crowd density estimation from video", US PAT 7,139,409 issued 9/2006.
- N. Paragios, Visvanathan R., Stenger B. Coetzee F.M, "Real-time crowd density estimation from video", US PAT 7,457,436 issued 11/2008.
- Coetzee F.M., Colfer C.M., Barron A., Unger J., Murphy J., Lerner G. "System and method for authenticating the source of marked objects", US PAT 20040125988 issed 7/2004.