The best way to make the modules stick is to build something. These five projects take you from machine learning fundamentals to a neural network written from scratch, a CNN image classifier, sentiment analysis on real reviews, and an LLM-powered chatbot.
Each one is a code-along video, so you can pause, build it yourself and adapt it to your own data. Pick the project that matches the module you've just finished and come back for the rest.
A hands-on walkthrough of supervised and unsupervised learning, covering classification, regression, and clustering, built in Google Colab with TensorFlow.
Build a neural network completely from scratch, with no TensorFlow or PyTorch, just NumPy and math, to classify handwritten MNIST digits.
Train a convolutional neural network on any set of images you like, then evaluate and test it on photos it hasn't seen before.
Use scikit-learn to turn product reviews into features and train a model that predicts whether a review is positive or negative.
Build a conversational chatbot with the GPT-4 API, complete with conversation memory and a typewriter-style chat interface.