Some of my own projects based on exercises from the textbook "Hands on Machine Learning with Scikit-Learn and Tensorflow"
Experimenting with various support vector classification hyperparameters on several different toy datasets, and visualizing classification decision regions with the mlxtend library
An implementation of a random forest from building up individual decision trees
Illustrating the steps of Principal Component Analysis and other dimensionality reduction approaches using the scikit-learn package for manifold learning. Visualizing some manifold learning algorithms like t-SNE, Isomap, and MDS applied to the MNIST dataset
Attempting to explain and illustrate kernel methods in non-linear support vector machines
Applying some ensemble methods like voting classifiers, bagging/pasting, AdaBoost, and gradient boosting and trying to visualize the collective decision regions on sample datasets
Some background on laplacian eigenmaps and spectral clustering/embedding