As a teaching assistant for a Machine Learning course, I found it usful to implement many of the algorithms from scratch. I have added notes on the derivation of each algorithm. I also compare the outputs with a library implementation such as sci-kit learn or PyTorch.
Algorithms covered in tutorials:
- Naive Bayes ✔️
- Linear Regression ✔️
- Support Vector Machines (SVM) (in-progress)
- Fully Connected Neural Networks ✔️
- K Nearest Neighbors (KNN) ✔️
- Decision Trees ✔️
- K-Means clustering ✔️
- Principal Component Analysis (PCA):heavy_check_mark:
Additional implementations:
- Logistic Regression ✔️
- Mixture of Gaussians ✔️