Lectures in course EE-311: Fundamentals of machine learning

Introduction to Machine Learning: Basics and Examples

Introduces the basics of machine learning, emphasizing the use of Piazza for class-related communications and practical exercises in Python.

Introduction to Machine Learning: Basics and Examples

Introduces the basics of machine learning, covering supervised learning, reinforcement learning, and dimension reduction.

Supervised Learning: Image Space and Labeling

Covers supervised learning, binary and multi-class classification problems, and making predictions from labeled examples.

Linear Regression: Parametric Models and Optimization

Covers linear regression, parametric models, optimization, and predictive modeling using labeled examples.

Unsupervised Learning: Clustering and Dimension Reduction

Covers unsupervised learning, clustering, and dimension reduction techniques.

Supervised Learning: Formalization and Cost Functions

Covers the formalism for supervised learning and decision functions in classification problems.

Multi-Class Classification: Approaches and Boundaries

Explains the strategies for multi-class classification and the concept of decision boundaries.

Hypothesis Space and Learning Task

Explores hypothesis space, supervised learning tasks, cost functions, and risk minimization in machine learning.

Binary Classification Cost Function

Explains the 0/1 cost function for binary classification and its impact on minimizing prediction errors.

Binary Classification by Regression: Decision Functions and Cost Functions

Explores binary classification by regression, decision functions, and various cost functions.

Cross-Entropy and Regression Cost Functions

Explores cross-entropy in classification and various regression cost functions.

Generalization and Overfitting

Covers generalization, overfitting, and model complexity in machine learning.

Convex Optimization: Examples of Convex Functions

Explores convex optimization, convex functions, and their properties, including strict convexity and strong convexity, as well as different types of convex functions like linear affine functions and norms.

Convex Optimization: Gradient Algorithms

Covers convex optimization problems and gradient-based algorithms to find the global minimum.

Parametric Regressions: Linear Regression

Explores parametric regressions, emphasizing linear regression's simplicity and complexity trade-offs between parametric and non-parametric models.

Logistic Regression and Polynomial Regression

Introduces logistic regression for binary classification and polynomial regression on polynomial variables.

Support Vector Machines: Definition and Separation Hyperplane

Covers the history, linear separability, hyperplanes, and support vectors in Support Vector Machines.

Support Vector Machine: Primal Formulation with Hard Margin

Covers the Support Vector Machine with a hard margin formulation and the importance of maximizing the margin between classes.

Support Vector Machines: Dual Formulation for Hard Margin

Explores the dual formulation of Support Vector Machines for hard margin classification.

Support Vector Machines: Soft Margin SVM

Introduces Soft Margin SVM, aiming to balance errors and margin width.