Arora S., Park S., Jacob D., Chen D. Introduction to Machine Learning

Princeton: LN, 2023. — 256 p.Supervised Learning.Linear Regression: An Introduction.
A Warm-up Example.
Using Linear Regression for Sentiment Prediction.
Importance of Featurization.
Linear Regression in Programming.
Statistical Learning: What It Means to Learn.
A Warm-up Example.
Summary of Statistical Learning.
Implications for Applications of Machine Learning.
Optimization via Gradient Descent.
Gradient Descent.
Implications of Linearity of Gradient.
Regularizers.
Gradient Descent in Programming.
Linear Classification.
General Form of a Linear Model.
Logistic Regression.
Support Vector Machines.
Multi-class Classification (Multinomial Regression).
Regularization with SVM.
Linear Classification in Programming.
Exploring ``Data Science'' via Linear Regression.
Boston Housing: Machine Learning in Economics.
fMRI Analysis: Machine Learning in Neuroscience.Unsupervised Learning.Clustering.
Unsupervised Learning.
Clustering.
K-Means Clustering.
Clustering in Programming.
Low-Dimensional Representation.
Low-Dimensional Representation with Error.
Application 1: Stylometry.
Application 2: Eigenfaces.
N-Gram Language Models.
Probabilistic Model of Language.
N-Gram Models.
Start and Stop Tokens.
Testing a Language Model.
Matrix Factorization and Recommender Systems.
Recommender Systems.
Recommender Systems via Matrix Factorization.
Implementation of Matrix Factorization.Deep Learning.Introduction to Deep Learning.
A Brief History.
Anatomy of a Neural Network.
Why Deep Learning?
Multi-class Classification.
Feedforward Neural Network and Backpropagation.
Forward Propagation: An Example.
Forward Propagation: The General Case.
Backpropagation: An Example.
Backpropagation: The General Case.
Feedforward Neural Network in Programming.
Convolutional Neural Network.
Introduction to Convolution.
Convolution in Computer Vision.
Backpropagation for Convolutional Nets.
CNN in Programming.Reinforcement Learning.Introduction to Reinforcement Learning.
Basic Elements of Reinforcement Learning.
Useful Resource: MuJoCo-based RL Environments.
Illustrative Example: Optimum Cake Eating.
Markov Decision Process.
Markov Decision Process (MDP).
Policy and Markov Reward Process.
Optimal Policy.
Reinforcement Learning in Unknown Environment.
Model-Free Reinforcement Learning.
Atari Pong (1972): A Case Study.
Q-learning.
Applications of Reinforcement Learning.
Deep Reinforcement Learning.Advanced Topics.Machine Learning and Ethics.
Facebook's Suicide Prevention.
Racial Bias in Machine Learning.
Conceptions of Fairness in Machine Learning.
Limitations of the ML Paradigm.
Final Thoughts.
Deep Learning for Natural Language Processing.
Word Embeddings.
N-gram Model Revisited.Mathematics for Machine Learning.Probability and Statistics.
Probability and Event.
Random Variable.
Central Limit Theorem and Confidence Intervals.
Final Remarks.
Calculus.
Calculus in One Variable.
Multivariable Calculus.
Linear Algebra.
Vectors.
Matrices.
Advanced: SVD/PCA Procedures.