- Robert C. Williamson,
*Number Theoretic Transform Convolver*, Bachelor of Engineering Thesis (Q.I.T. 1983). -
Robert C. Williamson,
*Software Implementation of Polynomial Transform based Convolution Algorithms*, Master of Engineering Science Thesis, (University of Queensland 1985). -
Robert C. Williamson,
*Probabilistic Arithmetic*," PhD Thesis, (University of Queensland 1989). Here is a Scanned version of thesis which has the pictures missing from the previous link, but is 12MB in size.

[P92] Peter L. Bartlett, Anthony Burkitt, and Robert C. Williamson (Editors),

[P152] David Helmbold and Bob Williamson (Editors),

[P8] Robert C. Williamson, "Interval Arithmetic and Probabilistic Arithmetic," in

[P107] Robert C. Williamson, Alex J.Smola and Bernhard Schölkopf, "Entropy Numbers, Operators, and Support Vector Kernels", chapter in

[P120] Alex J.Smola, Andreé Elisseff, Bernhard Schölkopf and Robert C. Williamson, "Entropy Numbers for Convex Combinations and MLPs," pages 369-387 in Alex Smola, Peter Bartlett, Bernhard Schölkopf and Dale Schuurmans (Editors),

[P158] Ralf Herbrich and Robert C. Williamson, Learning and Generalization: Theoretical Bounds, invited submission to Michael Arbib (Ed.)

[P94]

[P153] Darren B. Ward, Rodney A. Kennedy and Robert C. Williamson, "Constant Directivity beamforming," pages 3-17 in Michael Brandstein and Darren Ward (Eds)

[P138] Ralf Herbrich, Thore Graepel and Robert C. Williamson, The Structure of Version Space, pages 263-279 in

[P3] Robert C. Williamson and Tom Downs, "The Inverse and Determinant of a 2×2 Uniformly Distributed Random Matrix,"

[P5] Robert C. Williamson and Tom Downs, Probabilistic Arithmetic: Numerical Methods for Calculating Convolutions and Dependency Bounds

[P6] Robert C. Williamson, "An Extreme Limit Theorem for Dependency Bounds of Normalised Sums of Random Variables,"

[P7] Robert C. Williamson, "The Law of Large Numbers for Fuzzy Variables under a General Triangular Norm Extension Principle,"

[P18] Brian C. Lovell and Robert C. Williamson, The Statistical Performance of Some Instantaneous Frequency Estimators,,

[P34] Brian C. Lovell, Robert C. Williamson and Boaulem Boashash, The Relationship Between Instantaneous Frequency and Time Frequency Representations,

[P44] Robert C. Williamson,

[P45]

[P32]

[P43]

[P30] Robert C. Williamson and Uwe Helmke, "Existence and Uniqueness Results for Neural Network Approximations,",

[P31]

[P56]

[P33] Uwe Helmke and Robert C. Williamson, "Neural Networks, Rational Functions and Realization Theory"

[P54]

[P41]

[P55] Peter J. Kootsookos and Robert C. Williamson, "FIR Approximation of Fractional Sample Delay Systems"

[P46] Peter L. Bartlett and Robert C. Williamson, "The VC-Dimension and Pseudodimension of Two-Layer Neural networks with Discrete Inputs,"

[P61]

[P42]

ftp://trick.nte.springer.de/jmsec/85167.ps.

[P53] Peter L. Bartlett, Philip M. Long and Robert C. Williamson, "Fat-Shattering and the Learnability of Real-Valued Functions"

[P57]

[P64]

[P59]

[P63]

[P97] Darren B. Ward, Robert C. Williamson and Rodney A. Kennedy, "Broadband Microphone Arrays for Speech Acquisition," in

[P65]

[P77]

[P85] John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson and Martin Anthony, "Structural Risk Minimization over Data-Dependent Hierarchies",

[P88] Peter J. Kootsookos,

[P117]

[P78]

[P108]

[P93]

[P101]

[P115] Bernhard Schölkopf, Alex Smola, Robert Williamson and Peter Bartlett, "New Support Vector Algorithms,"

[P116] Alex J. Smola, Sebastian Mika, Bernhard Schölkopf and Robert C. Williamson, "Regularised Principal Manifolds",

[P128]

[P132] Bernhard Schölkopf, John C. Platt, John Shawe-Taylor, Robert C. Williamson and Alex J.Smola, "Estimating the Support of a High-Dimensional Distribution,", Microsoft technical report MSR-TR-99-87. Slightly abridged version in

[P102] Robert E. Mahony and Robert C. Williamson, "Prior Knowledge and Preferential Structures in Learning Algorithms,"

[P100] Robert C. Williamson, Alex Smola and Bernhard Schölkpof, "Generalization Performance of Regularization Networks and Support Vector Machines

[P133]

[P159] Ralf Herbrich and Robert C. Williamson, "Algorithmic Luckiness" Journal of Machine Learning Research

[P172] Jyrki Kivinen, Alexander J. Smola and Robert C. Williamson, Online Learning With Kernels,

[P142] Richard K. Martin, William A. Sethares, and Robert C. Williamson, "Exploiting Sparsity in Adaptive Filters,"

[P168] Darren B. Ward,

[P171]

[P173]

[P178] Sören Sonnenburg, Mikio L. Braun, Cheng Soon Ong, Samy Bengio, Leon Bottou, Geoffrey Holmes, Yann LeCun, Klaus-Robert Müller, Fernando Pereira, Carl Edward Rasmussen, Gunnar Rätsch, Bernhard Schölkopf, Alexander Smola, Pascal Vincent, Jason Weston and Robert Williamson, The Need for Open Source Software in Machine Learning ,

[P182] Mark D. Reid and Robert C. Williamson, Information, Divergence and Risk for Binary Experiments,

[P183] Mark D. Reid and Robert C. Williamson, Composite Binary Losses,

[P187] Tim van Erven, Mark D. Reid and Robert C. Williamson, ""Mixability is BAyes Risk Curvature Relative to Log Loss," submitted to

[P189] Elodie Vernet, Robert C. Williamson and Mark D. Reid, "Composite Multiclass Losses," in preparation for JMLR.

[P129] Robert C. Williamson, John Shawe-Taylor, Bernhard Schölkopf and Alex J. Smola, "Sample Based Generalization Bounds," accepted subject to revision to

[P89]

[P147] Ying Guo, Peter Bartlett, Alex J. Smola, Robert C. Williamson and Jonathan Baxter, "Norm-based Regularization of Boosting," submitted to

[P175] Adam Kowalczyk, Alex J. Smola and Robert C. Williamson, "Logic, Trees and Kernels, submitted to

[P181] Krzysztof A. Krakowski, Robert E. Mahony, Robert C. Williamson and Manfred K. Warmuth, A geometric View of Non-Linear On-Line Gradient Descent, submitted to JMLR, 2008. Here are the reviews

[P141] William A. Sethares, Richard K. Martin and Robert C. Williamson, "Apparatus and Method for Using Adaptive Algorithms to Exploit Sparsity in target Weight Vectors in an Adaptive Equalizer", United States Patent 7,061,977 B2. June 13, 2006.

[P2] R.C. Williamson and T. Downs, "Probabilistic Arithmetic and the Distribution of Functions of Random Variables,"

[P1] R.C. Williamson and L.C. Westphal, "Efficient Software Implementation of Cyclic Convolution Algorithms Based on Polynomial Transforms,"

[P4] Robert C. Williamson, "Interval Arithmetic and Probabilistic Arithmetic,"

[P9] Brian C. Lovell, Peter J. Kootsookos and Robert C. Williamson, "Efficient Frequency Estimation and Time-Frequency Representations,"

[P11] Robert C. Williamson, "ε-Entropy and the Complexity of Feedforward Neural Networks,"

[P10] Mark J. Damborg, Robert C. Williamson,

[P12] Brian C. Lovell, Peter J. Kootsookos and Robert C. Williamson, "The Circular Nature of Discrete-time Frequency Estimates,"

[P13] Peter L. Bartlett and Robert C. Williamson, "Perceptron Learning with Reasonable Distributions of Training Examples,"

[P14] Robert C. Williamson and William A. Sethares, "A Provably Convergent Perceptron-like Algorithm for Learning Hyper-cubic Decision Regions,"

[P15] Peter L. Bartlett and Robert C. Williamson, "Investigating the Distribution Assumptions in the PAC Learning Model,"

[P19]

[P20] Robert C. Williamson and Peter L. Bartlett, "Splines, Rational Functions, and Neural Networks,"

[P21]

[P35]

[P36]

[P37] Uwe Helmke and Robert C. Williamson "Rational Parametrizations of Neural Networks,"

[P38]

[P39]

[P80] Uwe Helmke and Robert C. Williamson, "Parametrization Aspects of Neural Networks and Linear System Theory,"

[P47]

[P48]

[P49] Peter L. Bartlett, Philip M. Long and Robert C. Williamson, "Fat-shattering and the learnability of real-valued functions",

[P50]

[P67]

[P68]

[P69]

[P71] A. Kowalczyk, J. Szymanski, and R.C. Williamson, "Learning Curves from a Modified VC-Formalism: a Case Study,",

[P81] John Shawe-Taylor, Peter Bartlett, Robert C. Williamson, Martin Anthony, "A Framework for Structural Risk Minimisation"

[P82]

[P70] A. Kowalczyk, J. Szymanski, P.L. Bartlett and R.C. Williamson, "Examples of Learning Curves from a Modified VC-Formalism,"

[P74] Peter J. Kootsookos,

[P75] Rodney A. Kennedy, Thushara Abhayapala,

[P72]

[P73]

[P83]

[P90] John Shawe-Taylor and Robert C. Williamson, "A PAC Analysis of a Bayesian Estimator",

[P84]

[P96] Robert C. Williamson, "Some Results in Statistical Learning Theory with Relevance to Nonlinear System Identification," IFAC Nonlinear Control Systems Design Symposium 1998 (NOLCOS98), Preprints, Volume 2, pages 443-448. To appear in the proceedings published by Elsevier

[P95]

[P98] Bernhard Schölkopf, Peter L. Bartlett, Alex Smola and Robert C. Williamson, "Support Vector Regression with Automatic Accuracy Control", In L. Niklasson and M. Boden and T. Ziemke (eds.). Proceedings of the 8th International Conference on Artificial Neural Networks, pp. 111 - 116, Springer Verlag, Perspectives in Neural Computing, Berlin.

[P106]

[P103] Robert C. Williamson, Alex J. Smola and Bernhard Schölkopf, "Entropy Numbers, Operators and Support Vector Kernels," Proceedings of the 4th European Conference on Computational Learning Theory (EUROCOLT'99), 285-300, (1999).

[P112] John Shawe-Taylor and Robert C. Williamson, "Generalization Performance of Classifiers in Terms of Observed Covering Numbers," Proceedings of the 4th European Conference on Computational Learning Theory (EUROCOLT'99), 274-284, (1999).

[P114] Alex J. Smola, Robert C. Williamson, Sebastian Mika and Bernhard Schölkopf, "Regularized Principal Manifolds," Proceedings of the 4th European Conference on Computational Learning Theory (EUROCOLT'99) 214-229, (1999)

[P111]

[P118] Ying Guo, Peter L. Bartlett, John Shawe-Taylor and Robert C. Williamson, "Covering Numbers for Support Vector Machines", Proceedings of the Twelfth Annual Conference on Computational Learning Theory, pages 267-277, 1999.

[P121]

[P124]

[P125] Darren B. Ward and Robert C. Williamson, "Beamforming for a Source Located in the Interior Field of an Array," Pages 873-876 in volume 2 of Proceedings of the Fifth International Sympoisium on Signal Processing and its Applications, (ISBN 1 86435 451 8) ISSPA99.

[P105] Bernhard Schölkopf, Alex J. Smola, Peter L. Bartlett and Robert C. Williamson, Shrinking the Tube: A new Support Vector Regression Algorithm, to appear in M. S. Kearns, S. A. Solla, and D. A. Cohn, editors, Advances in Neural Information Processing Systems 11, MIT Press, Cambridge, MA.

[P130] Paul D. Teal, Robert C. Williamson and Rodney A. Kennedy, "Error Performance of a Channel of Known Impulse Response", Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on , Volume: 5 , 2000 Page(s): 2733 -2736.

[P143] Marshall Shephard and Robert C. Williamson, "Very Low Voltage Power Conversion," Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on , Volume: 2 , 2001 Pages 289 -292 vol. 2.

[P123] Bernhard Schölkopf, John Shawe-Taylor, Alex Smola and Robert C. Williamson, "Kernel-Dependent Support Vector Error Bounds," Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470) , Volume: 1 , 1999

[P110]

[P134] Robert E. Mahony and Robert C. Williamson, Riemannian Structure of Some New Gradient Descent Learning Algorithms in Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communication and Control Symposium (AS-SPCC)), S. Haykin and J. Principe (Eds), IEEE Press, New Jersey, ISBN 0-7803-5800-7, pages 197-202.

[P127] Alex Smola, John Shawe-Taylor, Bernhard Schölkopf and Robert C. Williamson, "The Entropy Regularization Information Criterion," Advances in Neural Information processing Systems 12, (NIPS'99), pages 342-348, MIT Press, 2000.

[P135] Robert C. Williamson, Alex J. Smola and Bernhard Schölkopf, Entropy Numbers of Linear Function Classes Proceedings of COLT2000, 309-319, July 2000.

[P126] Bernhard Schölkopf, Robert C. Williamson, Alex Smola, John Shawe-Taylor and John Platt, "Support Vector Method for Novelty Detection," Advances in Neural Information processing Systems 12, (NIPS'99), pages 582-588, MIT Press, 2000.

[P137] Alex J.Smola, Zoltán Óvári and Robert C. Williamson, Regularization with Dot Product Kernels, Advances in neural Information processing Systems 13, (NIPS 2000), pages 308-314, 2001.

[P140] Thore Graepel, Ralf Herbrich and Robert Williamson, From Margin to Sparsity, Advances in neural Information processing Systems 13, (NIPS 2000), pages 210-216, 2001.

[P155] Ralf Herbrich and Robert C. Williamson, "Algorithmic Luckiness", Advances in Neural Information processing Systems 14, T. G. Dietterich, S. Becker and Z. Ghahramani (eds), MIT Press, 2002.

[P157] Darren B. Ward and Robert C. Williamson, Particle Filtering Beamformingfor Acoustic Source Localization in a Reveberant Environment, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2002), vol. II, pp.1777-1780, Orlando, FL, USA, May 2002.

[P91] Shahar Mendelson and Robert C. Williamson, "Agnostic Learning Nonconvex Function Classes", pages 1-13, in J. Kivinen and R.H. Sloan (Eds), Computational Learning Theory 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8-10, 2002. Proceedings Lecture Notes in Artificial Intelligence 2375.

[P164]

[P149] Jyrki Kivinen, Alex Smola, and Robert C. Williamson, "Online Learning with kernels", in NIPS2001.

[P148] Adam Kowalczyk, Alex Smola and Robert C. Williamson, "Kernel machines and Boolean functions" in NIPS2001.

[P162] Jyrki Kivinen, Alex Smola and Robert C. Williamson, Large Margin Classification for Moving Targets, ALT'02 (13th International Conference on Algorithmic Learning Theory), pages 113-127, Lecture Notes in Artificial Intelligence 2533,November 24-26, 2002.

[P122] Thore Graepel, Ralf Herbrich, Bernhard Schölkopf, Alex Smola, Peter Bartlett, Klaus-Robert Müller, Klaus Obermayer and Robert Williamson, "Classification on Proximity Data with LP-Machines," Ninth International Conference on Artificial Neural Networks, pages 304-309, London 1999.

[P150] Richard K. Martin, William A. Sethares, Robert C. Williamson and C. Richard Johnson Jr, Exploiting Sparsity in Adaptive Filters, Proceedings of 2001 Conference on Information Sciences and Systems, The Johns Hopkins University, March 2001.

[P160]

[P161]

[P165]

[P169]

[P166]

[P176] Omri Guttman, S.V.N. Vishwanathan and Robert C. Williamson Learnability of Probabilistic Automata via Oracles in

[P179] Mark D. Reid and Robert C. Williamson, Surrogate Regret Bounds for Proper Losses,

[P180] Mark D. Reid and Robert C. Williamson, Generalised Pinsker Inequalities, Conference on Learning Theory (COLT), 2009. (No page numbers: see www.cs.mcgill.ca/ ∼ colt2009/proceedings.html

[P184] Ulrike von Luxburg, Robert C. Williamson and Isabelle Guyon, ""Clustering: Science or Art?", JMLR Workshop and Conference Proceedings (to appear, 2011)

[P185] Mark D. Reid and Robert C. Williamson, ""Convexity of Proper Composite Binary Losses," Proc. of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS 2010).

[P186] Tim van Erven, Mark D. Reid and Robert C. Williamson, ""Mixability is Bayes Risk Curvature Relative to Log Loss", in COLT 2011.

[P188] Elodie Vernet, Robert C. Williamson and Mark D. Reid, Composite Multiclass Losses, to appear in NIPS 2011.

[P146]

[P174] Krzysztof Krakowski, Robert Mahony, Robert Williamson and Manfred Warmuth, Online Learning on Spheres submitted to COLT2005, January 2005.

[P16] Robert C. Williamson and William A. Sethares, "Learning Hyper-Cubic and Convex Polyhedral Decsion Regions Using Perceptron-Like Algorithms"

[P17] Robert C. Williamson, "ε-Entropy, Functional Representation and Feedforward Neural Networks",

[P22] Robert C. Williamson and Uwe Helmke, "Approximation Theoretic Results for Neural Networks"

[P23] Robert C. Williamson and Peter L. Bartlett, "Piecewise Linear Feedforward Neural Networks,"

[P40]

[P51]

[P52]

[P58]

[P66]

[P90]

[P60] Peter L. Bartlett and Robert C. Williamson, "The sample complexity of neural network learning with discrete inputs" Proceedings of Australian Conference on Neural Networks, pages 189-192, 1995

[P167]

[P131] John Shawe-Taylor and Robert C. Williamson, "Large Margin Classification" Tutorial presented at COLT'99.

[P163] Robert C. Williamson, Review of

[P136] Robert C. Williamson `Margins, Sparsity and Perceptrons', talk presented an Neural Networks 2000 (Workshop held in Graz, Austria, May 2000).

[P144] Robert C. Williamson, "Telephones," special invited lecture for ENGN1211

[P145] Robert C. Williamson, "Riemannian Structure of Some New Gradient Descent Learning Algorithms", talk given at ANU, 21/9/2000.

[P151] Robert C. Williamson, "SRM and VC Theory", talk presented at Dagstuhl on Inference Principles and Model Selection.

[P154] Robert C. Williamson, Incorporating Priors in Classical Gradient Descent Learning Algorithms talk given at Microsoft Research (Cambridge and Redmond), July/August 2001

[P156] Robert C. Williamson, "Inductive Principles," Talk presented at the Machine Learning Summer School. Canberra, February, 2002.

[P170] Robert C. Williamson, "Machine Learning - A Personal Introduction, presented at the Machine Learning Summer School, Canberra, February 2003.

[P24] Brian D.O. Anderson,

[P119] Bernhard Schölkopf, John Shawe-Taylor, Alex J. Smola and Robert C. Williamson, "Generalization Bounds via Eigenvalues of the Gram Matrix," Neurocolt TechReport NC2-TR-1999-035.

[P139] Bernhard Scholkopf, Ralf Herbrich, Alex J. Smola and Robert C. Williamson, A Generalized Representer Theorem, NeuroCOLT2 Technical report NC2-TR-2000-81. Submitted to NIPS 2000.

[P177] Eric A. Hehmann and Robert C. Williamson, "Posterior Cramer-Rao Bound for Acoustic Source Tracking in Reverberant Environments,", NICTA Technical Report, (2006).

[P79] Peter L. Bartlett and Robert C. Williamson, "Sample Complexity versus Approximation Error" (1993)

[P76]

[P26]

[P25] Robert C. Williamson and

[P27]

[P28]

[P29]

[P62]

[P86]

[P104] Alex J. Smola, Robert C. Williamson and Bernhard Schölkopf, "Generalization Bounds for Convex Combinations of Kernel Functions," Submitted to NIPS'98. NIPS did not like it. It has evolved into P120.

[P113] Bernhard Schölkopf, Alex J. Smola and Robert C. Williamson, "A New Parametrization of Support Vector Machines," submitted to the 4th European Conference on Computational Learning Theory (EUROCOLT'99). EUROCOLT did not like this. We turned it into P115.

[P87] Mario Marchand, John Shawe-Taylor and Robert C. Williamson, "Choosing Hyperplanes to Improve Generalization," In Preparation. 1996-7.

[P99] Robert C. Williamson, Bernhard Schölkopf and Alex Smola, "A Maximum Margin Miscellany", February 1999. (35 pages)

[P109] Robert C. Williamson, "Some Results in Statistical learning Theory with Relevance to Nonlinear System Identification," in preparation for submission to

File translated from T

On 26 Oct 2011, 11:46.