FOUNDATIONS OF MACHINE LEARNING
Foundations of Machine Learning
This course will teach you the foundations of modern machine learning. It is a fully web-based self-study course offered by Linköping University.
You will learn the underlying theory of machine learning by reading selected chapters from the book Machine Learning: A first course for engineers and scientists and get hands-on experience by solving exercises on this web platform.
Section 1: Introduction
Introduction to machine learning and the course structure
Section 2: Supervised Learning: a First Approach
Getting started with the k-Nearest Neighbor method
Section 3: Basic Parametric Models and a Statistical Perspective on Learning
Exploring parametric models through linear and logistic regression
Section 4: Understanding, Evaluating and Improving Performance
Learning approaches for model validation and selection
Section 5: Neural Networks and Deep Learning
Achieving model flexibility with deep architectures
Section 6: Generative Models and Learning from Unlabeled Data
Modeling the distribution of the input
Section 7: User Aspects of Machine Learning
Practical and ethical considerations
Section 8: Outlook
What happens next?
Teachers on the course
Course director and examiner
How do I apply to this course?
I'm admitted to the course. What happens next?
How do I activate my LiU ID?
This webpage contains the course materials for the course ETE370 Foundations of Machine Learning.
The content is licensed under Creative Commons Attribution 4.0 International.
Copyright © 2021, Joel Oskarsson, Amanda Olmin & Fredrik Lindsten