If you are looking for the textbook itself, you will find it in the "chapter pdfs" folder. Source .tex files are stored in the "chapters" folder.
This is the machine learning textbook I am developing in collaboration with MIT's 6.3900 staff. I'm placing this in a secondary repo so I can share it with friends and other who may be interested.
The content of this class includes concepts such as:
- Regression and Classification
- Hypotheses and Hypothesis Classes
- Validation, Cross-Validation, and Hyperparameter Tuning
- Linear and Logistic Hypotheses
- Batch and Stochastic gradient descent
- Feature transformations of data
- Clustering and non-parametric methods
- Neural networks and back-propagation
- Convolutional and Recurrent Neural Networks
- State Machines
- Markov Decision Processes
- Reinforcement Learning, Q-Learning
- Matrix Calculus, Auto-Encoders
The goal of this text is to be as easily understood by new students as possible, with the complete willingness to sacrifice concision or elegance for that purpose. If there are any apparent errors, or something that seems at all confusing, feel free to contact me!