Course information
Instructor: Dr. Theodora Chaspari
Credits: 3
Syllabus (Fall 2021): here
Roadmap (Fall 2021): here
Class final projects (Fall 2017): here
Course description
Machine learning is a sub-field of Artificial Intelligence that gives computers the ability to learn and/or act without being explicitly programmed. Applications of machine learning have permeated many aspects of every-day life and can be found among others in self-driving cars, speech recognition, computer vision, and genomics. Topics include supervised and unsupervised learning (including parametric and non-parametric models, clustering, dimensionality reduction, deep learning), optimization procedures, and statistical inference. The objective of this course is to teach fundamental methods of machine learning with focus on the theoretical underpinnings, practical implementations, and experimentation.
Resources
Lecture 1: Introduction to Machine Learning (slides)
Lecture 2: K-Nearest Neighbor classifier (slides)
Lecture 3: Linear perceptron algorithm (slides)
Lecture 4: Linear regression (slides)
Lecture 5: Logistic regression (slides)
Lecture 6: Multilayer perceptron (slides)
Lecture 7: Deep learning (slides)
Lecture 8: Decision trees and random forests (slides)
Lecture 9: Ensemble learning (slides)
Lecture 10: Dimensionality reduction and feature selection (slides)
Lecture 11: Clustering (slides)
Lecture 12: Explainable AI (slides)
Lecture 13: AI Fairness (slides)
Handouts
Math symbols (handout)
Vector perpendicular to line (handout)
Linear perceptron practice problem (handout)
Linear regression optimization (handout)
Regularized regression (handout)
Maximum likelihood estimation (handout)
Logistic regression optimization (handout)
Regularized logistic regression (handout)
Proof outline of back-propagation (handout)
Example of back-propagation (handout)
Neural networks handout (handout)
Decision trees example (handout)
Regression trees example (handout)
Adaboost example (handout)
PCA proof outline (handout)
Hierarchical clustering example (handout)
GMM example (handout)