Machine Learning UWR 2020

About

Assigments and syllabus from Machine Learning @ University of Wrocław 2020 Class

Notebooks issue

Sometimes jupyter notebooks doesn't render. Use this in case https://nbviewer.jupyter.org.

Syllabus

1. Introduction to ML Supervised Learning - Unsupervised Learning
2. K-nearest neighbors
3. Linear Regression
4. High Bias - High Variance
5. Regularization
6. Ridge Regression
7. Quantile regression
8. Parameters - Hyperparameters
9. Statistical inference
10. Naive Bayes Classifier
11. Logistic Regression
12. Gradient Descent
13. Logistic Regression for multiclass classification
14. Huber - pseudo-Huber Loss
15. A General and Adaptive Robust Loss Function
16. Feature Selection
    • Scoring Based Methods
    • Wrapper Methods
    • LASSO
    • LARS
17. Decision Trees
    • Purity Criterions
    • Categorical - Numerical splits
    • Dealing with Missing values
    • DT for regression
    • Pruning
18. Classifier Bagging
19. Random Forest
20. Boosting
21. AdaBoost
22. XGBoost
23. Neural Networks Intuitions
24. Kernels
25. SVM
26. Simplified PAC Theory
27. K-means
28. Online K-means
29. Kohonen Maps
30. Gaussian and EM
31. Principal component analysis
32. Probabilistic Graphical Models

Project

@ https://github.com/lekcyjna123/UWrMLProjectAudioSeg

Kaggle InClass Competition

As part of Assignment 4, a Kaggle Competition was held, involving the use of feature selection methods to select the best features from corputed medical data:

https://www.kaggle.com/c/rank-the-features