Courses in summer term 2008 / Seminar on Semi-supervised Learning / readings:
Due four weeks after end of term
30 pages at most,
3 hard copies(printed) and 1 soft copy (CD).
Note on Grades:
Marks will be based on presentation (including answers to questions), seminar paper, and
general participation (e.g., asking questions),
bonuses for own experiments or implementations. If any, please also include in the CD.
readings
Note on Seminar Paper :
List of readings (ee = link to electronic edition; ask me for the other references):
-
Introduction
- .
18.06 Introduction to Supervised Learning.
Speaker: Söhren Kampf
- [ee] S. B. Kotsiatis (2006): Supervised Machine Learning: A Review of Classification Techniques Informatica 31.
- 25.06 Introduction to Unsupervised Learning. Speaker: Christoph Jäger Generative Models
-
Co-Training Algorithm.
- [ee] A. Blum, T. Mitchel (1998): Combining Labeled and unlabeled data with Co-Training Conference on computational learning.
-
Kernel Methods and Fisher Kernel.
- [ee] Tommi S. Jaakkola, F.L. Chung, R. Luk , C.M. Ng (1998): Exploiting generative models in discriminative classifiers Proceedings of the 1998 conference on Advances in neural information processing systems II.
-
02.07 Semi-Supervised Text Classification Using EM
.
Speaker:Alexander Hundt
- O. Chapelle, B. Schölkopf, A. Zien (2006): Semi-Supervised Text Classification Using EM Semi-Supervised Learning, pp. 33--56.
-
Risks of Semi-Supervised Learning.
- O. Chapelle, B. Schölkopf, A. Zien (2006): Risks of Semi-Supervised Learning Semi-Supervised Learning, pp. 57-71.
-
Probabilistic Semi-Supervised Clustering with Constraints
.
- O. Chapelle, B. Schölkopf, A. Zien (2006): Probabilistic Semi-Supervised Clustering with Constraints Semi-Supervised Learning, pp. 73-101.
Low-Density Separation
-
Transductive Support Vector Machines
.
- O. Chapelle, B. Schölkopf, A. Zien (2006): Transductive Support Vector Machines Semi-Supervised Learning, pp. 105-116.
-
Gaussian Processes and the Null-Category Noise Model
- O. Chapelle, B. Schölkopf, A. Zien (2006): Gaussian Processes and the Null-Category Noise Model Semi-Supervised Learning, pp. 137-149.
Graph-Based Methods
-
09.07 Label Propagation in Graphs
Speaker: Alexander Schmehl
- O. Chapelle, B. Schölkopf, A. Zien (2006): Label Propagation in Graphs Semi-Supervised Learning, pp. 193-215.
-
Semi-Supervised Learning with Conditional Harmonic Mixing
- O. Chapelle, B. Schölkopf, A. Zien (2006): Semi-Supervised Learning with Conditional Harmonic Mixing Semi-Supervised Learning, pp. 251-273.
Change of Representation
-
Spectral Methods for Dimensionality Reduction
- O. Chapelle, B. Schölkopf, A. Zien (2006): Spectral Methods for Dimensionality Reduction Semi-Supervised Learning, pp. 293-306.
Semi-Supervised Learning in Practice
-
Semi-Supervised Protein Classification Using Cluster Kernels
- O. Chapelle, B. Schölkopf, A. Zien (2006): Semi-Supervised Protein Classification Using Cluster Kernels Semi-Supervised Learning, pp. 343-358.
-
Prediction of Protein Function from Networks
- O. Chapelle, B. Schölkopf, A. Zien (2006): Prediction of Protein Function from Networks Semi-Supervised Learning, pp. 361-376.