Xi Li (李溪)
she/her/hers
Assistant Professor, Ph.D.
University of Alabama at Birmingham
CS685/785 Foundation of Data Science
Course Overview
This course explores essential concepts and techniques in statistical inference and big data analytics. It covers a broad spectrum of topics, including data fundamentals, analysis in high-dimensional spaces, singular value decomposition (SVD), principal component analysis (PCA), random walks, and Markov Chains. Additionally, it includes a special topic on the ethical implications of big data -- security, privacy, and fairness, explored through reading research papers. Students will engage in practical learning through coding assignments and hands-on projects to gain practical experience and exposure to cutting-edge techniques.
Course Objectives
Throughout this course, students will:
- Gain hands-on experience with data science Python libraries, including NumPy, Pandas, and scikit-learn.
- Learn basic concepts and theories in data science.
- Understand the ethical implications of data science and explore state-of-the-art works in this domain.
Topics
- Data Fundamentals
- High-Dimensional Space
- Singular Value Decomposition (SVD) and Principal Component Analysis (PCA)
- Random Walks and Markov Chains
- Ethics in Data Science: Security, Privacy, and Fairness
Prerequisites
Basic concepts of linear algebra, calculus, probability theory, and programming skills in Python.
Textbook
Foundation of Data Science (2018), Avrim Blum, John Hopcroft and Ravindran Kannan Online
Grading Policy
- Assignments: 20%
- Mini Project: 20%
- Midterm Exam: 20%
- Final Exam: 30%
- Participation: 10%
Course Activities
Assignments: This course includes 4-5 written assignments to enhance learning. All assignments must be completed individually, as teamwork is not permitted.
Mini Project: The mini project in this course allows students to select from a range of topics for exploration and analysis. Students are permitted to form teams. A report is required, which will encapsulate the project’s methodology, analysis, and individual contributions.
- Master’s students can form teams of up to 5 members and produce a minimum 4-page report.
- PhD students may form a team of up to 3 members and produce a report of at least 8 pages. Additionally, PhD students are required to present their findings in class, showcasing their collaborative work and insights.
Exams: Exams are conducted in a closed-book format to assess your understanding and integration of the course material. Questions are accessible via Canvas on a phone or laptop The final exam is a comprehensive test covering all topics discussed throughout the semester.
Participation: Participation is assessed through in-class quizzes. Quizzes consist of multiple-choice questions accessible via Canvas on a phone or laptop.