Machine Learning in Practice

Garant předmětu:

Daniel Vašata

Lecturer:

Jan Hučín

Tutor:

Jan Hučín

Supervisor:

Department of Applied Mathematics

Synopsis:

Applying machine learning methods to real projects in practice involves many other necessary tasks - from understanding the intentions of the client to, ideally, technical implementation. The course guides students through all phases of a project according to the standard CRISP-DM methodology, not only theoretically but also practically. The aim is to experience real data processing and learn how to describe the whole process from exploration to evaluation of the model performance in the form of a clear and understandable report.

Requirements:

BI-ML1/BI-ML2

Syllabus of lectures:

1. Machine learning in the context of Data science projects. CRISP-DM methodology.

2. Basic technologies for data analysis and processing.

3. Data understanding.

4. Statistical inference.

5. Applied Bayesianism.

6. Creating a comprehensible report.

7. Data preparation.

8. Modeling practice and model evaluation.

9. Interpretability of models.

10. Application of SW engineering principles.

11. Use of technologies for Big Data.

12. Limits of statistical methods.

Syllabus of tutorials:

1. Hands-on experience with selected technologies (pandas, scikit-learn, seaborn, mlflow, ...)

2. Basic exploration and visualization, formulation of findings and recommendations for data cleaning.

3. Practical problem solving using Bayesian reasoning.

4. Report generation tools (Quarto, pretty-jupyter, ...)

5. Real data processing: data transformation and feature extraction, 6. building a reference model and improving it.

Study Objective:

The course aims to give students insight into a project-based approach to solving real-world machine learning projects. The aim is to experience real data processing and, following the standard CRISP-DM methodology, learn to describe the whole process from exploration to evaluation of model performance in the form of a clear and understandable report.

Study materials:

1. Hastie, T. - Tibshirani, R. - Friedman, J. : The Elements of Statistical Learning, Data Mining, Inference and Prediction. Springer, 2011. ISBN 978-0387848570.

2. Murphy, K. P. : Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series). MIT Press, 2012. ISBN 978-0262018029.

Note:

Further information:

https://courses.fit.cvut.cz/NI-MLP/

Time-table for winter semester 2024/2025:

Time-table is not available yet

Time-table for summer semester 2024/2025:

Time-table is not available yet

The course is a part of the following study plans:

• Master specialization Computer Science, in Czech, 2018-2019 (elective course)
• Master specialization Computer Security, in Czech, 2020 (elective course)
• Master specialization Design and Programming of Embedded Systems, in Czech, 2020 (elective course)
• Master specialization Computer Systems and Networks, in Czech, 202 (elective course)
• Master specialization Management Informatics, in Czech, 2020 (elective course)
• Master specialization Software Engineering, in Czech, 2020 (elective course)
• Master specialization System Programming, in Czech, version from 2020 (elective course)
• Master specialization Web Engineering, in Czech, 2020 (elective course)
• Master specialization Knowledge Engineering, in Czech, 2020 (elective course)
• Master specialization Computer Science, in Czech, 2020 (elective course)
• Mgr. programme, for the phase of study without specialisation, ver. for 2020 and higher (elective course)
• Study plan for Ukrainian refugees (elective course)
• Master specialization System Programming, in Czech, version from 2023 (elective course)
• Master specialization Computer Science, in Czech, 2023 (elective course)