Explore comprehensive machine learning concepts through this university-level lecture series covering fundamental algorithms, theoretical foundations, and practical applications. Begin with supervised learning fundamentals and decision trees, then progress through linear models, online learning algorithms, and the perceptron algorithm. Delve into computational learning theory including PAC learning, Occam's razor, and VC dimension concepts that form the theoretical backbone of machine learning. Master advanced techniques such as boosting, ensemble methods, and support vector machines while understanding stochastic gradient descent optimization. Examine the relationship between discriminative and generative models, explore Bayesian learning approaches, and study logistic regression for classification tasks. Conclude with an introduction to neural networks and practical considerations for implementing machine learning systems in real-world scenarios.

Syllabus

Machine Learning: Lecture 1: Introduction
Machine Learning: Lecture 1: Course information
Machine Learning: Lecture 2: Supervised Learning - The setup
Machine Learning: Lecture 3a: Supervised Learning - The Setup (continued)
Machine Learning: Lecture 3b: Decision Trees
Machine Learning: Lecture 4: Decision trees (continued)
Machine learning: Lecture 5a: Decision trees and overfitting (continued)
Machine learning: Lecture 5b: Linear Models
Machine Learning: Lecture 6a: Linear models (continued)
Machine Learning: Lecture 6b: Online learning
Machine Learning: Lecture 7: Online Learning (continued)
Machine Learning: Lecture 8a: Online Learning (continued)
Machine Learning: Lecture 8b: Perceptron
Machine Learning: Lecture 9: Perceptron (continued)
Machine Learning: Lecture 10: Perceptron (continued)
Machine Learining: Lecture 11: Least Mean Square Regression
Machine Learning: Lecture 12a: Least mean square regression (continued)
Machine Learning: Lecture 12b: Computational Learning Theory
Machine Learning: Lecture 13: PAC learning
Machine Learning: Lecture 14: Occam's razor (continued)
Machine Learning: Lecture 15: Mid-semester review
Machine Learning: Lecture 16a: Learnability results
Machine Learning: Lecture 16b: Agnostic learning
Machine Learning: Lecture 17a: Agnostic learning (continued)
Machine Learning: Lecture 17b: Shattering and VC dimension
Machine Learning: Lecture 18a: VC dimensions (continued)
Machine Learning: Lecture 18b: Boosting and Ensembles
Machine Learning: Lecture 19: Boosting and ensembles (continued)
Machine Learning: Lecture 20: Support Vector Machines
Machine Learning: Lecture 21: Support Vector Machines (continued)
Machine Learning: Lecture 22: Stochastic Gradient Descent for SVM
Machine Learning: Lecture 23a: Learning as loss minimization
Machine learning: Lecture 23b: Bayesian learning
Machine Learning: Lecture 24a: Bayesian learning (continued)
Machine Learning: Lecture 24b: Discriminative and Generative models
Machine Learning: Lecture 25: Logistic regression
Machine Learning: Lecture 25: Introduction to neural networks
Machine Learning: Lecture 27: Neural networks (continued)
Machine Learning: Lecture 28: Practical concerns