Estimated schedule:

Week 2: Introduction, Cluster software, K-means algorithm, Divisive algorithm
Week 3: Agglomerative algorithms, Clustering software (CB*)
Week 4: Randomized local search, Genetic algorithms
Week 5: Number of clusters, Distance metrics, Binary data, Fast search methods
Week 6: Dimensionality, visualization, Outlier detection, Gaussian mixture models
Week 7: Very large data sets, SOM, missing data
Week 8: (only exercises)
Week 9: (exercises + grading session)

Lecture Notes:

Part 1 - Introduction
Part 2a - K-means algorithm
Part 2b - Divisive algorithms
Part 2c - Agglomerative clustering algorithms
Part 2d - Local search algorithms
Part 2e - Genetic algorithms
Part 3 - Number of clusters
Part 4 - Distance metrics
Part 5 - Fast search methods
Part 6 - Dimensionality
Part 6b - Isomap algorithm
Part 6c - Principal component analysis
Part 7 - Outlier removal
Part 8 - Gaussian mixture model
Part 8b - Random Swap EM
Part 9 - Self-organizing map
Part 10 - Very large data sets

Course project tasks

Other material:

Collection of clustering programs
Data sets
Cluster software - visualization tool
3-d visualization software
Pseudo codes
Collection of material
Binaries for CS (18.1.12)
sample.cb
sample2.cb
Sample NN graphs
F-ratio for S1
F-ratio for S2
F-ratio for S3
F-ratio for S4

Articles and links:

Article about Split-based algorithm (pdf) (Word)
Article about PNN algorithm (pdf) (Word)
Article about Fast PNN algorithm (pdf) (Word)
Article about Iterative Shrinking algorithm (pdf) (Word)
Article about Fast K-means algorithm (pdf) (Word)
Article about RLS algorithm (pdf) (Word)
Article about GA algorithm (pdf) (Word)
Improved version of the GA algorithm (pdf) (Word)
Article about Delta-SC cost function (pdf)
Article about GMG algorithm (pdf)
Ville Hautamäki's Phd Thesis (pdf)
Olli Virmajoki's Phd Thesis (pdf)
Mantao Xu's Phd Thesis (pdf)
Ismo Kärkkäinen's Phd Thesis (pdf)
Marko Tuononen's MSc Thesis (pdf)
Svetlana Cherednichenko's MSc Thesis (pdf)
K-MST based clustering
Presentation material from Caiming Zhong
Presentation material from Sami Äyrämö
Presentation material from Jarkko Venna
IEEE Xplore archive (available via Campus computers)
Science Direct (available via Campus computers)