CS446/ECE449: Machine Learning (Spring 2024)

Course Information

The goal of machine learning is to develop algorithms and models that enable computers to learn from data and make predictions or decisions without being explicitly programmed for a particular task. In this course we will cover three main areas, (1) supervised learning, (2) unsupervised learning, and (3) reinforcement learning. In particular we will cover the following: perceptron, decision trees, Naive Bayes, Gaussian Bayes, linear regression, logistic regression, support vector machines, learning theory, deep learning, structured methods, kMeans, Gaussian mixtures, expectation maximization, VAEs, GANs, Markov decision processes, Q-learning and Reinforce.

Pre-requisites: Probability, linear algebra, and proficiency in Python.

Recommended Text:
(1) Probabilistic Machine Learning: An Introduction [KM]
(2) Deep Learning [GBC]
(3) Understanding Machine Learning: From Theory to Algorithms [SB]
(4) The Elements of Statistical Learning: Data Mining, Inference, and Prediction [HTF]
(5) Deep Learning: Foundations and Concepts [BB]
(6) Reinforcement Learning: an Introduction [SB+]

Course Deliverables:
(1) Homework due at 23:59pm, see below for dates
(2) Midterm
(3) Final

Grading:
3 credit: Homework 60% (drop 1 homework), Midterm 20%, Final 20%
4 credit: Homework 60% (drop 0 homework), Midterm 20%, Final 20%

Grading policy is subject to change.

Late Policy: Each student will have a 3-day grace period in total for the homework assignments. You may use this grace period for any homework assignment throughout the semester. After the grace period, late homework will be penalized 20% per day. Students with legitimate reasons (special accommodations, see below) who contact the professor before the deadline may apply for an extension.

---

Instructor & TAs

---