Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2024/2025

Advanced machine learning

The course is not on the list Without time-table
Code Completion Credits Range Language
NI-AML Z,ZK 5 2P + 1C English
Garant předmětu:
Lecturer:
Tutor:
Supervisor:
Department of Applied Mathematics
Synopsis:

The course introduces students to selected advanced topics of machine learning and artificial intelligence. The topics present techniques in the field of recommendation systems, image processing, control and interconnection of physical laws with the field of machine learning.

The aim of the exercise is to familiarize students with the methods discussed.

Requirements:

Recommended prerequisite is „NI-MVI Computational Inteligence Methods“ course. We assume knowledge of forward, convolution neural networks, autoencoders, transformers.

Syllabus of lectures:

1. Introduction, Repeatable ML Projects - MLOps

2. Optimisation in Deep Learning

3. Recommender Systems

4. Recommender Systems

5. Continual Learning

6. ML in modeling and control

7. Advanced Image Processing

8. Physics informed ML

9. Interpretable and Explainable Models

10. Causal Machine Learning

11. Time Series Modeling

12. AI Alignment

Syllabus of tutorials:

1. Optimisation in Deep Learning

2. Recommender Systems

3. ML in modeling and control

4. Physics informed ML

5. Interpretable and Explainable Models

6. Semestral project presentation

Study Objective:

The course introduces students to selected advanced topics of machine learning and artificial intelligence. The topics present techniques in the field of recommendation systems, image processing, control and interconnection of physical laws with the field of machine learning.

Study materials:

[1] Silva, N., Werneck, H., Silva, T., Pereira, A. C., & Rocha, L. (2022). Multi-Armed Bandits in Recommendation Systems: A survey of the state-of-the-art and future directions. Expert Systems with Applications

[2] McAuley, J. (2022). Personalized Machine Learning. Cambridge University Press.

[3] Gift, N., & Deza, A. (2021). Practical MLOps. „ O'Reilly Media, Inc.“.

[4] Rajendra, P., Ravi. PVN, H., & Naidu T, G. (2021). Optimization methods for deep neural networks. In AIP Conference Proceedings (Vol. 2375, No. 1, p. 020034). AIP Publishing LLC.

[5] Bagus, B., Gepperth, A., & Lesort, T. (2022). Beyond Supervised Continual Learning: a Review.

[6] Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422-440.

[7] Kirchner, J. H., Smith, L., Thibodeau, J., McDonell, K., & Reynolds, L. (2022). Researching Alignment Research: Unsupervised Analysis.

[8] Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society

[9] Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P. A. (2019). Deep learning for time series classification: a review. Data mining and knowledge discovery

Note:
Further information:
http://courses.fit.cvut.cz/NI-AML
No time-table has been prepared for this course
The course is a part of the following study plans:
Data valid to 2024-04-17
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/en/predmet7416006.html