Honors College Thesis
 

Open, online, interactive visualizations for learning about Gaussian mixture models

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/honors_college_theses/73666d50m

Descriptions

Attribute NameValues
Creator
Abstract
  • We construct a website to explain how Gaussian mixture models can be optimized using the expectation maximization algorithm. Previous free, online material on this process has been extremely limited. All sources surveyed failed to entirely describe our identified criteria for an in-depth description and useful visualizations. After surveying a variety of online sources, and researching attributes of useful visualizations for students, we use libraries including Threejs and React-Three-Fiber to construct a website that satisfies our identified criteria. The result is a free, open source web-site that anyone with a background in calculus and statistics can use to understand and implement Gaussian mixture models optimized with the expectation maximization algorithm. Further research may include more in depth evaluation methods of the effectiveness of this site, and implementations of other explanatory websites on lesser known machine learning topics using our methods. The site is available at the following link: https://gmmthesissite.netlify.app/
  • Key Words: Gaussian Mixture Models, Computer Science Education, Scientific Visualization
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Non-Academic Affiliation
Rights Statement
Related Items
  • Website: An Introduction to Gaussian Mixture Models
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details AllenStuart2023.pdf 2023-06-06 Public Download