| Title: | Machine Learning |
|---|---|
| Course Section Number: | CSC-271-01 |
| Department: | Computer Science |
| Description: | Machine Learning: How does Alexa recognize your speech? How does Gmail filter spam from your inbox? How does Facebook identify you in photographs? How does Netflix recommend what movies you should watch? How does 23andMe link genetic factors to diseases? How does DeepMind develop artificial intelligence programs that can beat world champions in Chess and Go? Algorithms that automatically transform data into intelligent decision-making processes are now ubiquitous in society. The convergence of "big data" with massively parallel computational hardware has led to a renaissance in the exciting world of machine learning. This course will be an introduction to the theory and practice of machine learning. We will develop the foundations of machine learning, guided by principles such as Occam's razor and in consideration of hinderances such as the dreaded "curse of dimensionality". We will explore training and evaluation frameworks. We will look at a variety of tasks including classification, regression, clustering and reinforcement learning. We will learn about models such as decision trees, Bayesian learning, kernel methods, neural networks and deep learning. Prior experience with linear algebra and vector calculus are not required, but will be helpful for this course. |
| Credits: | 1.00 |
| Start Date: | August 22, 2019 |
| End Date: | December 15, 2019 |
| Meeting Information: |
08/22/2019-12/05/2019 Lecture Tuesday, Thursday 01:10PM - 02:25PM, Goodrich Hall, Room 101
|
| Faculty: | McCartin-Lim, Mark |
| Requisite Courses: | Prerequisite: CSC-111 or permission of the instructor., Prerequisite: MAT-112 or permission of the instructor. |
Course Status
| Section Name/Title | Status | Dept. | Capacity |
Enrolled/ Available/ Waitlist |
|---|