Machine Learning 2

Relations:

The course 01SU2 can be graded only after the course 01SU1 has been successfully completed.

Course guarantor:

Filip Šroubek

Lecturer:

Filip Šroubek

Tutor:

Jiří Franc, Filip Šroubek

Supervisor:

Department of Mathematics

Synopsis:

1.Fundamental topics from the probability theory and machine learning (classical distributions, Bayes’ theorem, Kullback-Leibler divergence, curse of dimensionality, overfitting, maximum likelihood and maximum a posteriori estimators, Principle Component Analysis)

2.Decision trees: general schema, recursive partitioning, optimal partitioning and pruning, ensemble learning - bagging, boosting, random forests.

3.Examples of decision trees: Adaptive boosting – AdaBoost, Gradient boosting, Xgboost.

4.Numerical methods for optimization (steepest descent, conjugate gradient, Newton and quasi-Newton, constrained extrema, Lagrangian).

5.Deep feedforward networks (hidden units, nonlinear activation functions, output units, loss functional, stochastic gradient descent, back-propagation algorithm)

6.Optimization for training deep models (regularization, algorithms with adaptive learning rates)

7.Convolutional neural networks

8.Recurrent neural networks

9.Advanced network architectures (autoencoders, Generative Adversarial networks)

10.Applications of deep learning (classification, segmentation, image reconstruction)

Requirements:

Syllabus of lectures:

visit https://su2.utia.cas.cz/

Syllabus of tutorials:

visit https://su2.utia.cas.cz/

Study Objective:

Study materials:

Key references:

[1] Goodfellow I., Bengio Y., Courville A.: Deep Learning, MIT Press, 2016.

[2] Bishop, Christopher M.: Pattern Recognition and Machine Learning. Springer, 2006.

Recommended references:

[3] Géron A: Hands-On Machine Learning with Scikit-Learn and TensorFlow, 2017.

[4] Chollet, F.: Deep Learning with Python, 2018.

[5] online resources: pytorch.org/tutorials/, playground.tensorflow.org, tensorflow.org/learn/

Note:

Further information:

https://su2.utia.cas.cz/

Time-table for winter semester 2024/2025:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon	room Šroubek F. 09:00–12:50 (lecture parallel1)
Tue
Wed
Thu
Fri

Time-table for summer semester 2024/2025:

Time-table is not available yet

The course is a part of the following study plans:

• Aplikované matematicko-stochastické metody (compulsory course in the program)
• Aplikace informatiky v přírodních vědách (elective course)