Essential Machine Learning for Physicists
Course 0000003806 in WS 2023/4
General Data
| Course Type | lecture |
|---|---|
| Semester Weekly Hours | 2 SWS |
| Organisational Unit | Department of Physics |
| Lecturers |
Zinonas Zinonos Assistants: Richard Fuchs |
| Dates |
Wed, 12:00–14:00, LMU-HS and 3 singular or moved dates |
Assignment to Modules
-
NAT3009: Grundlagen des "Machine Learning" für die Physik / Essential Machine Learning for Physicists
This module is included in the following catalogs:- Specific catalogue of special courses for condensed matter physics
- Specific catalogue of special courses for nuclear, particle, and astrophysics
- Specific catalogue of special courses for Biophysics
- Specific catalogue of special courses for Applied and Engineering Physics
Further Information
Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.
| additional remarks | Are you ready for absolute Machine Learning domination?This course is designed to be the physicists' most complete source for learning how stuff works in Machine Learning and how this can be applied to physics research problems involving big scientific data. You will be walked step-by-step into the world of Artificial Intelligence with real applications in Physics. With every lecture and tutorial, you will develop new skills and improve your understanding of this challenging yet emerging field of Data Science.This course is fun and exciting, but at the same time, we will be diving deep into the deep grounds of Machine Learning!Outlined ContentThe course is designed to cover the following areas: > Data Management and Data Visualization > Data Preprocessing and Feature Engineering > Supervised Learning: * Regression tasks * Classification tasks > Capstone Projects with Big Data > Unsupervised Learning: Clustering methods > State-of-art machine learning libraries such as XGBoost, Microsoft's LightGB > Dimensionality Reduction > How to deploy trained predictive modelsDetailed ContentThe course will be structured in the following way:Part 0: Data Management & Data Visualization> NumPy> Pandas Dataframes> Data visualization with Python libraries (Matplotlib, Seaborn)Part 1: Data Preprocessing & Feature Engineering> Handle missing data> Encode categorical (nominal and ordinal) data> Handle outliers> Feature scaling> Data partitioning into train and test samples> Imputation of missing class values Part 2: Machine Learning Preamble> Machine Learning Landscape> Elements of the Bias-Variance trade-off in Machine Learning tasks Part 3: Regression> Simple Linear Regression> Multiple Linear Regression> Polynomial Regression> Support Vector Regression> Decision Tree Regression> Random Forest RegressionPart 4: Regression Project> Train a regression model on big data and make predictions> Control model overfitting & underfitting> Regression metrics> Feature selection> Model optimization with hyperparameter grid search > Cross-validation> Model evaluation> Full model training and deployment to make predictionsPart 5: Classification> Logistic Regression> Support Vector Machines> Kernel SVM> Naive Bayes> Decision Tree Classification> Random Forest Classification> Boosting methodsPart 6: Classification Project> Train a classification model on big data and make predictions> Control model overfitting & underfitting> Control data label imbalance> Classification metrics> Feature selection> Model optimization with hyperparameter grid search > K-fold cross-validation> Model evaluation> Full model training and deployment to make predictionsPart 7: State-of-art machine learning libraries> XGBoost> CatBoost (Yandex)> LightGBM (Microsoft)Part 8: Dimensionality Reduction> Principle Component Analysis> Linear Discriminant Analysis> Kernel PCAPart 9: Clustering> k-Means Clustering> Hierarchical Clustering> Density-Based Spatial ClusteringPart 10: Model Deployment at Scale> Model persistence> Model APIBy the end of the semester, Machine Learning will be completely demystified and you should be able to apply Machine Learning techniques to all of your use cases. |
|---|---|
| Links |
Course documents E-Learning course (e. g. Moodle) TUMonline entry TUMonline registration |
Equivalent Courses (e. g. in other semesters)
| Semester | Title | Lecturers | Dates |
|---|---|---|---|
| WS 2022/3 | Essential Machine Learning for Physicists | Zinonos, Z. |
Wed, 12:00–14:00, LMU-HS and singular or moved dates |