Mathematical Foundations of Machine Learning

Note

For those who are interested in audenting this course, the schedule is MWF 3:05 - 3:50 at Peabody Hall Classroom 0309 or use the zoom link. The material is available at the Uark GitLab repository. Both the zoom link and GitLab repo require a UARK account. You can also email me for more information.

Course Description

This is an introductory course to Machine Learning (ML). ML is a powerful technique widely used in data-driven areas such as language processing, face recognition, image segmentation, banking, finance, insurance, drug discovery, engineering, etc. We will commence with an introduction to Python, highlighting prominent packages and standard datasets pivotal to the field. As we delve deeper, students will be introduced to a range of ML algorithms such as linear regression, logistic regression, k-means, k-nearest neighbors (KNN), support vector machine (SVM), Na”ive Bayes, Hopfield Network, decision trees, random forest, gradient boosting tree, deep neural networks (artificial neural network, ANN), graph neural networks, and manifold learning techniques.

Course Content

• Introduction to Machine Learning
• Data Preprocessing
• Topological Data Analysis
• Linear Regression

Discussion

• 1. Linear Regression - from scratch by PyTorch

Course Materials

We have made the code, homework, and lab materials for this course available in the UARK GitLab repository. Access to UARK’s GitLab requires either a VPN or on-campus connection, along with a UARK account. You can access the repository here if you are one of the students in my class or a UARK colleague interested in this course. If you’re interested in accessing this repository and are not part of the UARK community, please email me at jiahuic@uark.edu.