|
|
Section for Cognitive Systems |
DTU Informatics |
|
02459 Course Material Download
Documents are available as Adobe Acrobat PDF, zip'ed PostScript or links.
Software are stored as zip files.
Click here for help om file formats.
Lecture 1: Bayesian learning, factor models and approximate inference
- Lecture handout: Bayesian learning, factor models and approximate inference [PDF].
Background reading and resources
- Pattern Recognition and Machine Learning, Christopher M. Bishop, Springer (2006), Chapter 2.3, 2.4 and 10-12. [HTML]
Lecture 2: Sparse Kernel Machines
- Lecture handout: Sparse Supervised Learning Models [PDF].
- Lecture handout: Machine Learning for Sound Processing [PDF].
Background reading and resources
- D.J.C. MacKay: ``Applications of Bayesian neural networks.´´ [PDF], [HTML].
- C. K. I. Williams and C. E. Rasmussen: ``Gaussian processes for regression,'' in D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 514-520. The MIT Press, Cambridge, MA, 1996. [PDF].
- C.E. Rasmussen and C.K.I. Williams: ``Gaussian Processes for Machine Learning,''
The MIT Press, 2006. ISBN 0-262-18253-X. Overview, [Ch. 1: Introduction, PDF], Ch. 2: Regression [PDF], [Ch. 8: Approximations, PDF].
- J. Quiñonero-Candela and C. E. Rasmussen: ``A unifying view of sparse approximate Gaussian process regression,'' Journal of Machine Learning Research, 6:1935-1959, 12 2005. [PDF].
- D.J.C. MacKay: ``Gaussian Processes - A Replacement for Supervised Neural Networks?,'' Lecture notes for a tutorial at NIPS 1997. [PDF], [HTML].
- Michael E. Tipping, “Sparse bayesian learning and the relevance vector machine,” Journal of Machine Learning Research,
vol. 1, pp. 211-244, 2001. [PDF].
- Joaquin Quiñonero-Candela and Lars Kai Hansen: ``Bayesian Methods, Kernel Methods, Time series prediction,''International Conference on Acoustics, Speech, and Signal Processing, pp. 985-988, 2002. [PDF].
- Jan Larsen: ``Gaussian Integrals,'' DTU Informatics, 2003. [PDF].
- C. Rasmussen: ``Advances in Gaussian Processes,'' tutorial at NIPS2006. [HTML], [Lecture slides, PDF].
- Gaussian process web resources. [HTML].
- C. Rasmussen: Gaussian process MATLAB code. [Documentation, HTML], [ZIP].
- S. Sigurdsson: MFCC MATLAB code, DTU Informatics,DTU. [ZIP].
- A. Meng: MAR MATLAB code, DTU Informatics,DTU. [ZIP].
- Datasets
- Sunspot data [ASCII].
- Mackey-Glass data [ZIP].
- Santa Fe time series competition data description [HTML], [ZIP].
- The CATS Benchmark [HTML], [ASCII].
- Advanced Black-Box Techniques for Nonlinear Modeling: Theory and Applications [HTML]
- Eunite competition [html]
Lecture 3: Continuous latent variables
- Lecture handout 2: Continuous Latent Variable Models PCA, ICA, model selection. [PDF]
- Exercise instruction. [PDF]
Background reading and resources
- L.K. Hansen, J. Larsen and T. Kolenda ``On Independent Component Analysis for Multimedia Signals,'' in L. Guan, S.Y. Kung and J. Larsen (eds.) Multimedia Image and Video Processing, CRC Press, Ch. 7, pp. 175-199, 2000. [PDF].
Project 1: Song features for meta data classification
- Sound resources. [HTML].
- Sethares, W.A.; Morris, R.D.; Sethares, J.C.: "Beat Tracking of Musical Performances Using Low-Level Audio Features,"
IEEE Transactions on Speech and Audio Processing, Issue Vol.13 Issue.2, 2005. [PDF]
- Eric D. Scheirer: "Tempo and beat analysis of acoustic musical signals,"
J. Acoust. Soc. Am. 103 (1), January 1998, pp. 588-601. [PDF].
- Jonathan Foote Matthew Cooper Unjung Nam: "Audio Retrieval by Rhythmic Similarity," Third International Symposium on Musical Information Retrieval, September 2002, Paris. [PDF].
- Meng, A., Ahrendt, P., Larsen, J., Hansen, L. K., "Temporal Feature Integration for Music Genre Classification, IEEE Transactions on Audio and Speech and Language Processing," 2006. [HTML]
- Meng, A., Ahrendt, P., Larsen, J., Improving Music Genre Classification by Short-Time Feature Integration, IEEE International Conference on Acoustics, Speech, and Signal Processing,
2005. [HTML].
- Ahrendt, P., Meng, A., Larsen, J., ``Decision time horizon for music genre classification using short time features, EUSIPCO 2004, pp.
1293-1296, 2004. [HTML].
- IMSIR - The International Society for Music Information Retrieval [HTML]
Project 2: Instrument detection
- Nielsen, A. B., Sigurdsson, S., Hansen, L. K., Arenas-García, J.. "On the relevance of spectral features for instrument classification", IEEE International Conference on Acoustics, Speech, and Signal Processing, Honolulu, Hawaii, 2007.
[HTML].
- Y. Zhang and C. Zhang "Separation of Music Signals by Harmonic Structure Modeling", NIPS2005. [PDF].
- Intelligent Sound MATLAB toolbox (provided by the teachers).
Project 4: Modelling fMRI data by kernel PCA and ICA
- F.Aa. Nielsen, M.S. Christensen, K.M. Madsen, T.E. Lund, L.K.\ Hansen:
"fMRI Neuroinformatics", IEEE Engineering in Medicine and Biology Magazine, vol. 25(2), pp. 112-119, IEEE, 2006
[PDF].
- L.K. Hansen, "Multivariate strategies in functional magnetic resonance imaging,"
Brain and Language, 2007. [HTML].
Project 5: Social networks - Community detection by spectral clustering
- Ulrike von Luxburg: "A Tutorial on Spectral Clustering,"
Max Planck Institute for Biological Cybernetics.
[PDF]
- S. Lehmann, L.K. Hansen:
"Deterministic modularity optimization," European Physical Journal B 60(1) 83-88 (2007).
[PDF]
Project 6: Sparse Factor Models
- M. West. Bayesian factor regression models in the "large p, small n"
paradigm. In
J. Bernardo, M. Bayarri, J. Berger, A. Dawid, D. Heckerman, A. Smith, and M. West, editors, Bayesian Statistics 7, pages 723–732. Oxford University Press, 2003.
- J. Lucas, C. Carvalho, Q. Wang, A. Bild, J.R. Nevins, and M. West.
Bayesian Inference for
Gene Expression and Proteomics, chapter Sparse Statistical Modeling in Gene Expression Genomics, pages 155–176. Cambridge University Press, 2006.
- Z. Ghahramani, T.L. Gri?ths, and P. Sollich. Bayesian nonparametric latent feature mod- els. In J. Bernardo, M. Bayarri, J. Berger, A. Dawid, D. Heckerman, A.
Smith, and
M. West, editors, Bayesian Statistics 8, pages 201–226. Oxford University Press, 2006.
Project 8: Analysis of NETFLIX recommendation data
Project 9: Infinite mixture models
- Rasmussen, C. E.: The Infinite Gaussian Mixture Model. Advances in Neural Information Processing Systems 12, 554-560. (Eds.) Solla, S. A., T. K. Leen and K. R. Müller, MIT Press (2000)
[PDF]
- Neal, R. M., Markov chain sampling methods for Dirichlet process mixture models, Computational and Graphical Statistics, Journal of, 2000, 9, 249-265
[PDF]
- D. Görür, Nonparametric Bayesian Discrete Latent Variable Models for Unsupervised Learning. PhD thesis, TU Berlin, April 2007
[PDF]
Project 10: Slice sampling
- Neal, R. M., Slice sampling, Annals of Statistics, 2003, 31, 705-767
[PDF]
Project 11: Graph based semi supervised learning
- Risi Imre Kondor, John Lafferty, Diffusion Kernels on Graphs and Other Discrete Input Spaces, Proceedings of the Nineteenth International Conference on Machine Learning 2002, 315-322 [PDF]
For further information, please contact
- Associate Professor, Ph.D.
Ole Winther,
e-mail: owi@imm.dtu.dk,
Phone, +45 45253895
- Professor, Ph.D.
Lars Kai Hansen,
e-mail: lkhansen@imm.dtu.dk,
Phone, +45 45253889
- Associate Professor, Ph.D.
Jan Larsen,
e-mail: jl@imm.dtu.dk,
Phone, +45 45253923