Aims and objectives of the course
Knowledge of the most important concepts and methods form the area
adaptive filters, machine learning and neural networks.
- Introduction to Machine Learning
- Learning Algorithms for Neural Networks
- Learning Algorithms and Signal Processing: adaptive
- Algorithm independent Machine Learning
- Practical Classification Algorithms
- Unsupervised Learning
- Hidden Markov Models
- Application of HMMs to Speech Recognition
Übungen / Tutorials
- Getting started
- Introduction to the
Matlab Neural Network Toolbox (NNT)
- Using the NNT to solve
a digit classification task
- Software for Classification and Regression
- Comparing classification algorithms
- PCA, ICA, Blind Source
- Hidden Markov
- Mixtures of
- Automatic Speech
There are no particular courses which must be taken as
prerequisites for this course. Although there will be an
introduction to MATLAB in the beginning of the exercises, it is
recommended to have already some basic knowledge and experience in
it. We also assume elementary mathematical knowledge in probability
theory, statistics, analysis and calculus.
Bibliography and Teaching aids
- [DHS] R. O. Duda, P.E. Hart, D. G. Stork: Pattern
Classification, 2nd edition, John Wiley & Sons, 2001. (The publisher provides all figures in PDF format as well as a list of errata) 30 copies are available
- [BIS06] C. Bishop: Pattern Recognition and Machine Learning, Springer,
2006, 12 copies are available in the
- [BIS] C. Bishop: Neural Networks for Pattern Recognition, Oxford Univ.
- [HAY] S. Haykin: Neural Networks: A Comprehensive Foundation,
Macmillan/IEEE Press, 1994, 8 copies available in the
- [HKP] J. Hertz, A. Krogh, and R. G. Palmer. Introduction to the Theory of Neural Computation.
Addison Wesley, 1991. [amazone]
- [NNT] Documentation (pdf) to the Matlab Neural Network Toolbox.
- [HA1] S. Haykin: Adaptive Filter Theory, Third
Edition, Prentice-Hall, Inc., Upper Saddle River, NJ, 1996.
- [WS] B. Widrow and S. D. Stearns: Adaptive Signal
Processing, Prentice-Hall, Inc., Upper Saddle River, NJ, 1985.
- [BNT] K. Murphy: Bayes Net Toolbox for Matlab.
- [BIL] J. Bilmes: A Gentle Tutorial on the EM Algorithm and its Application to
Parameter Estimation for Gaussian Mixture and Hidden Markov
Models, Technical Report, University of Berkeley,
- [VB] VOICEBOX: Speech Processing Toolbox for
- [RAB] L. R. Rabiner: A tutorial on hidden Markov models and selected
applications in speech recognition, Proceedings of the IEEE, 77
- [HTK] S. Young, G. Evermann, T. Hain, D. Kershaw, G.
Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland:
- [HAH] X. Huang, A. Acero, H.Hon: Spoken Language
processing: A Guide to Theory, Algorithm and System Development,
Prentice Hall, Redmond, Washington, 2001.
- [RJ] L. R. Rabiner, B. Juang: Fundamentals of Speech
Recognition, PTR Prentice Hall (Signal Processing Series),
Englewood Cliffs NJ, 1993, ISBN 0-13-015157-2.
- [GM] B.Gold, N. Morgan: Speech and audio signal
processing: processing and perception of speech, and music, John
Wiley and Sons Inc., 1999, ISBN: 0471351547.