This might have been one of my favorite classes that I took during my undergradute career. It was a nice mix and balance of theory behind many foundational machine learning algorithms - from simple supervised algorithms such regression flavors, classifiers, and the intuition behind neural networks, to exploring newer, modern machine learning algorithms - analyzing unsupervised learning techniques by looking at latent spaces first through the lens of bottlenecking with autoencoders, to tokenizing segments and sequences with transformers.
Below are some of my notes that I think helped me understand many of the algorithms we learned below.