Skip to main content
Skip header

Praktický úvod do strojového učení

Type of study Bachelor
Language of instruction Czech
Code 653-2248/01
Abbreviation PUSU
Course title Praktický úvod do strojového učení
Credits 5
Coordinating department Department of Materials Engineering and Recycling
Course coordinator Ing. Lukáš Halagačka, Ph.D.

Subject syllabus

1. Familiarity with the Python environment and installation of data processing and machine learning libraries
2. Working with data, representing data structures and basic statistical indicators
3. Analyzing numerical and mixed data using the Pandas library
4. Basic functions from the Scikit-learn library for linear regression
5. Example problems and solutions using nonlinear regression
6. Multilayer neural networks
7. Applications of deep neural networks using the PyTorch library suitable for dynamic problem-solving
8. Solving a practical image classification problem using the presented numerical tools
9. An introductory description of the TensorFlow library used for deep learning and visualization in the private domain

Literature

NORGAARD, M. Neural networks for modelling and control of dynamic systems: a practitioner's handbook. Advanced textbooks in control and signal processing. London: Springer, c2000. ISBN 1-85233-227-1.

Advised literature

JHA, A.R. Mastering PyTorch: Build powerful neural network architectures using advanced PyTorch 1. x features. Packt Publishing Ltd, 2021.
MCKINNEY, Wes. Python for data analysis: Data wrangling with Pandas, NumPy, and IPython." O'Reilly Media, Inc.", 2012.

https://pytorch.org/tutorials/
https://pandas.pydata.org
https://www.tensorflow.org/learn