Seminar of Machine Learning
Code | Completion | Credits | Range | Language |
---|---|---|---|---|
01SUS | Z | 2 | 1P+0C | Czech |
- Garant předmětu:
- Lecturer:
- Tutor:
- Supervisor:
- Department of Mathematics
- Synopsis:
-
The aim of this course is to provide an introduction to machine learning, data mining and statistical image recognition. Main attention is paid to the basic methods of learning with the teacher, cluster analysis and dimensionality reduction. The lectures and theory explanation is accompanied by examples of experiments and practical applications.
- Requirements:
- Syllabus of lectures:
-
1) Introduction to machine learning, history and development of machine learning methods, necessary theory of probability and statistics.
2) Learning without a teacher - Clustering, K-means, Ward‘s methods, MBC, EM algorithm.
3) Learning with a teacher, description of basic methods, k-NN, Linear discrimination (Fisher, Bayes), logistic regression
4) Support vector machine, Linear and nonlinear SVM, core functions.
5) Model validation, binary classification (Accuracy, specificity, sensitivity, ROC curve), loss function, overtraining, model re-learning, cross-validation, bootstrap.
6) Dimensionality reduction, features selection, PCA (SVD), projection pursuit.
7) Decision trees, recursive division, divide and conquer, best division, pruning, random forests.
8) Introduction to neural networks, perceptron, MLP, backpropagation.
9) Examples of real applications
- Syllabus of tutorials:
- Study Objective:
- Study materials:
-
Key references:
[1] Ch. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.
[2] A. C. Müller, S. Guido, Introduction to Machine Learning with Python: A Guide for Data Scientists, O'Reilly, 2016
Recommended references
[3] Duda R.O. et al., Pattern Classification, (2nd ed.), John Wiley, New York, 2007
Study materials:
Complete lecture and exercises materials will be provided on the website.
- Note:
- Further information:
- No time-table has been prepared for this course
- The course is a part of the following study plans: