Date | Topic | Lecturer | |
---|---|---|---|
0 | 7th of February | GNU R and its usage | Sven Laur |
I | 14th of February | Decision trees and association rules | Sven Laur |
II | 21th of February | Linear models and polynomial interpolation | Anna Leontjeva |
III | 28th of February | Performance evaluation measures | Anna Leontjeva |
IV | 6th of March | Numeric optimization methods for continuous functions | Konstantin Tretjakov |
V | 13th of March | Linear classification | Konstantin Tretjakov |
VI | 20th of March | Feed-forward neural networks for prediction tasks | Sven Laur |
VII | 27th of March | Basics of probabilistic modelling | Sven Laur |
VIII | 3th of April | Maximum likelihood and maximum a posteriori estimates | Sven Laur |
IX | 10th of April | Model-based clustering techniques | Meelis Kull |
X | 17th of April | Expectation-maximisation and data augmentation algorithms | Meelis Kull |
XI | 24th of April | Factor analysis: PCA, LDA and ICA | Kristjan Korjus |
-- | 1st of May | International Workers' Day | V.I.Lenin |
XII | 8th of May | Statistical learning theory | Sven Laur/Jüri Lember |
XIII | 15th of May | Support Vector Machines | Konstantin Tretjakov |
XIV | 22th of May | Other kernel methods | Konstantin Tretjakov |
XV | 29th of May | Basics of ensemble methods | Raivo Kolde |
XVI | ??? | Particle filters | Raivo Kolde |
Before you submit the solutions
- Requirements to solutions of home exercises!
- Maximum points for the homework is 10 points. Additional points are not taken into account. They are not bonus tasks!
0. GNU R and its usage
Given by Sven Laur
Brief summary: Brief introduction to GNU R. GNU R as a calculator. GNU R as programming language. How to get data into R and how to get data out of R. Data frames and their manipulations.
Techniques for computing basic statistics and drawing plots. Loops and if brances.
Slides: PDF
Literature
Home exercises:
- No home exercises for this exercise session
I. Decision trees and association rules
Given by Sven Laur
- Home exercises to the I session
- Deadline: February 21
Example solutions
II. Linear regression
Given by Anna Leontjeva
- Home exercises to the II session
- Deadline: February 28
Example solutions
III. Performance evaluation measures
Given by Anna Leontjeva
- Home exercises to the III session
- Deadline: March 6
Example solutions with additional comments
IV. Optimization basics
Given by Konstantin Tretyakov
- Home exercises to the IV session
- Sample solutions Δ
- Deadline: March 13
V. Linear classification
Given by Konstantin Tretyakov
- Home exercises to the V session
- linear_class.R
- Sample solutions Δ
- Deadline: March 20
VI. Feed-forward neural networks
Given by Sven Laur
- Home exercises to the VI session
- R functions to visualise and manipulate neural networks
- The code written in practice session
- Deadline: March 27
Example solutions with additional comments
VII. Basics of probabilistic modelling
Given by Sven Laur
VIII. Maximum likelihood and maximum a posteriori estimates
Given by Sven Laur
IX. K-means and Gaussian mixture models
Given by Meelis Kull
- Home exercises to the IX session (updated April 13)
- The code written in practice session
- Video: http://uttv.ee/naita?id=10719 (Please log in to the UTTV system with ut account)
- Sample solutions Δ
- Deadline: April 17
X. Bernoulli mixture models and EM
Given by Meelis Kull
- Home exercises to the X session
- Data input and visualization code to download
- Data file to download
- Another data file to download
- Video: http://uttv.ee/naita?id=10800 (Please log in to the UTTV system with ut account)
- Sample solutions Δ
- Deadline: April 24
XII. Statistical Learning Theory and No Free Lunch Theorems
Given by Sven Laur
- Home exercises to the XII session
- The code written in practice session and some helper functions
- Video: http://uttv.ee/naita?id=11439 (Please log in to the UTTV system with ut account)
- Deadline: May 15
XIII. Support Vector Machines
Given by Konstantin Tretyakov
- Home exercises to the XIII session
- svm_base.r
- Video
- Sample solutions Δ
- Deadline: May 22
XIV. Kernel methods
Given by Konstantin Tretyakov
- Home exercises to the XIV session
- kernel_base.r
- reuters.txt.gz
- Video
- Sample solutions Δ
- Deadline: May 29
XV. Ensemble methods
Given by Raivo Kolde
- Home exercises to the XV session
- Data for the home exercise
- Deadline: 1 day before exam