Variational Bayes
W.D. Penny and S.J. Roberts (2000)
Notes on Variational Learning
Technical Report PARG-00-1, Department of Engineering Science, Oxford
University.
W.D. Penny and S.J. Roberts (2000)
Variational Bayes for 1-dimensional mixture models
Technical Report PARG-00-2, Department of Engineering Science, Oxford University. An earlier version of this paper contained an incorrect expression for the KL divergence between
two Dirichlet densities. This version contains the correct expression.
Bayesian Autoregressive Models
W.D. Penny and S.J. Roberts (2000)
Variational Bayes for Generalised Autoregressive Models
Technical Report PARG-00-12, Department of Engineering Science, Oxford University.
W.D. Penny and S.J. Roberts (2000)
Bayesian Multivariate Autoregressive Models with Structured Priors
Technical Report PARG-00-11, Department of Engineering Science, Oxford University.
W.D. Penny and S.J. Roberts (2000)
Bayesian Methods for Autoregressive Models
IEEE Workshop on Neural Networks for Signal Processing, Sydney Australia, December 2000.
W.D. Penny and S.J. Roberts (2000)
Variational Bayes for Non-Gaussian Autoregressive Models
IEEE Workshop on Neural Networks for Signal Processing, Sydney Australia, December 2000. The paper that appears in the actual conference proceedings
contains an incorrect expression for the KL divergence between
two Dirichlet densities. This version contains the correct expression.
Independent Component Analysis
R. Choudrey, W.D. Penny and S.J. Roberts (2000)
An Ensemble Learning Approach to Independent Component Analysis
IEEE Workshop on Neural Networks for Signal Processing, Sydney Australia, December 2000.
W.D. Penny, S.J. Roberts and R. Everson (2000)
ICA: Model-order selection and dynamic source models
In S.J. Roberts and R. Everson (Eds.) ICA: Principles and Practice,
Cambridge University Press, pp. 299-314.
W.D. Penny, R. Everson and S.J. Roberts (1999)
Hidden Markov Independent Component Analysis
In M Girolami (Ed.) Advances in Independent Component Analysis, Springer (2000).
W.D. Penny, S.J. Roberts and R. Everson (2000)
Hidden Markov Independent Components for Biosignal Analysis
Proceedings of MEDSIP-2000, International Conference on Advances in
Medical Signal and Information Processing, IEE, pp. 244-250.
Bayesian Neural Networks
W.D. Penny, D. Husmeier and S.J. Roberts (1999)
The Bayesian Paradigm: second generation neural computing
In P. Lisboa (Ed.) Artificial Neural Networks in Biomedicine ,
Springer-Verlag.
D. Husmeier, W. D. Penny and S. J. Roberts (1999). An Empirical Evaluation of Bayesian Sampling with Hybrid Monte Carlo for
Training Neural Network Classifiers. Neural Networks Vol 12, pp. 677-705.
Dirk Husmeier, William D. Penny, Stephen J. Roberts (1998). Empirical Evaluation of Bayesian Sampling for Neural Classifiers. in: L.Niklason,
M.Boden, T.Ziemke (Eds.), ICANN 98: Proceedings of the 8th International Conference on Artificial Neural Networks , Springer Verlag,
Perspectives in Neural Computing, pp. 323-328.
W.D. Penny and S.J. Roberts (1998).
Bayesian neural networks for classification: how useful is the evidence framework ? Neural Networks , Vol 12, pp. 877-892.
Stephen J. Roberts, Dirk Husmeier, Iead Rezek & Will Penny (1998).
Bayesian Approaches to Gaussian Mixture Modelling.
IEEE Transactions on Pattern Analysis and Machine
Intelligence, Vol 20, No. 11, pp. 1133-1142.
Hidden Markov Models
W.D. Penny and S.J. Roberts (1998)
Hidden Markov Models with Extended Observation Densities
Technical Report TR-98-15, Department of Electrical Engineering, Imperial College.
W.D. Penny and S.J. Roberts (1999)
Dynamic models for nonstationary signal segmentation .
Computers and Biomedical Research. Vol 32, No.6, December,pp.483-502.
A longer technical report version is available
here.
W.D. Penny and S.J. Roberts (1998).
Gaussian Observation Hidden Markov Models for EEG analysis. Technical Report TR-98-12, Department of Electrical Engineering, Imperial College.
Other Nonstationary Models
W.D. Penny, S.J. Roberts (1999)
Dynamic Logistic Regression
In Proceedings IJCNN'99 .
W.D. Penny, S.J. Roberts (1999)
Nonstationary Logistic Regression
Technical Report, Department of Electrical Engineering, Imperial College.
W.D. Penny and S.J. Roberts (1998).
Dynamic Linear Models, Recursive Least Squares and Steepest Descent Learning. Technical Report TR-98-13, Department of Electrical Engineering, Imperial College.
Error bars
W.D. Penny, D. Husmeier and S.J. Roberts (1999).
Covariance-based weighting for optimal combination of
model predictions ICANN-99 , Vol 2, pp. 826-831. Longer,
earlier technical report here .
W.D. Penny and S.J. Roberts (1998).
Error bars for linear and nonlinear neural network regression models.
Technical Report, Department of Electrical Engineering, Imperial College.
S.J. Roberts and W.D. Penny (1996).
A Maximum Certainty Approach to Feedforward Neural Networks.
Electronic Letters , 29(15),1340-1341.
S.J. Roberts, W.D. Penny, D. Pillot (1996)
Novelty, Confidence & Errors in Connectionist Systems.
Proceedings of IEE Colloquium on Intelligent Sensors and Fault
Detection , September 1996, 1996/261 : 10/1-10/6.
Brain Computer Interfacing
S.J. Roberts and W.D. Penny (2000)
Real-time Brain Computer Interfacing: a preliminary study using Bayesian learning Medical and Biological Engineering and Computing , Vol 38, No. 1, pp.56-61, 2000.
W.D. Penny, S.J. Roberts, E. Curran and M. Stokes(2000)
EEG-based communication: a pattern recognition approach IEEE Transactions on Rehabilitation Engineering, Vol 8, No. 2, June.
W.D. Penny, S.J. Roberts and M. Stokes(1999)
EEG-based communication: a pattern recognition approach Brain-Computer Interface Technology: Theory and practice. First International Meeting, Rensselaerville, New York, June 1999.
W.D. Penny and S.J. Roberts (1999)
Experiments with an EEG-based computer interface Technical Report, Department of Electrical Engineering, Imperial College.
W.D. Penny, S.J. Roberts (1999)
EEG-based communication via dynamic neural network models
In Proceedings IJCNN'99 .
W.D. Penny, S.J. Roberts and M.J. Stokes (1998).
Imagined Hand Movements Identified from the EEG Mu-Rhythm.
Technical Report. Department of Electrical Engineering, Imperial
College .
S.J. Roberts, W. Penny & I.Rezek (1998).
Temporal and Spatial Complexity measures for EEG-based Brain-Computer
Interfacing. Medical & Biological Engineering and
Computing, Vol 37, No. 1, pp. 93-99.
W.D. Penny and S.J. Roberts (1997).
Bayesian neural networks for detection of imagined finger movements from
single-trial EEG. Technical Report, Department of Electrical Engineering, Imperial College.
Other Biomedical Applications
W.D.Penny and D.Frost (1997). Neural network modelling of the level of observation decision in an acute psychiatric ward. Computers and Biomedical Research , 30, 1-17.
W.D.Penny and D.Frost (1996). Modelling psychiatric decisions with linear regression
and neural networks. In J.Taylor (Ed.) Neural networks and their applications ,
John Wiley.
Neural Network Tutorials
S.J. Roberts & W.D. Penny (1996).
Neural Networks : Friends or Foes? Sensor Review . 17(1),64-70.
W.D.Penny and D.Frost (1996). Neural networks in clinical medicine. Medical Decision Making , 16(4),386-398.
Digital Neural Networks
W.D.Penny and T.J.Stonham (1995). Generalization in multilayer sigma-pi networks. IEEE transactions on Neural Networks , 6(2), 506-508.
W.D.Penny and T.J.Stonham (1993) Storage capacity of multilayer boolean neural networks. Electronics Letters , 29(15), 1340-1341.