Syllabus: CIS 4930/5930 Advanced Artificial Intelligence Summer 2025
Syllabus: CIS 4930/5930 Advanced Artificial Intelligence Summer 2025
This course offers a comprehensive introduction to the core principles, algorithms, and practical tools of modern machine learning. It covers both theoretical foundations and hands-on methods for pattern recognition and data-driven decision making. Students will explore supervised and unsupervised learning techniques, with a focus on key topics such as linear and logistic regression, k-nearest neighbors, decision trees, support vector machines, boosting, and neural networks, including convolutional neural networks (CNNs). The course also delves into clustering, principal component analysis (PCA), and probabilistic approaches such as maximum likelihood estimation (MLE), maximum a posteriori (MAP) estimation, and naïve Bayes classifiers. Optimization methods like gradient descent and foundational models like the perceptron are also discussed. Applications include computer vision, bioinformatics, speech recognition, and social network analysis.
This course requires knowledge of basic computer science, math, algorithms and complexity, and programming principles.
We will not be strictly following any single textbook in this course. However, Probabilistic Machine Learning: An Introduction by Kevin Murphy and Pattern Classification by Richard O. Duda, Peter E. Hart, and David G. Stork broadly cover the course material and are recommended resources.
Python
Time: Tuesday and Thursday 9:45AM - 11:20AM
Location: HCB 0212
Instructor: Ang Li (Email: al23bp at fsu dot edu)
The instructor’s office hour is Tuesday 12:00PM-1:00PM at 166 Love Building.
Teaching Assistant: TBD
Course Website: https://www.causalds.org/teaching/cis_4930/5930
Grades will be computed based on the following factors:
Homework 14% (20% for CIS 4930)
Challenge Homework Questions 6% (Extra credits for CIS 4930)
Project 40%
Midterm 20%
Final 20%
Letter Grades: The letter grades will be assigned according to the following criteria, and if necessary, the grades will be curved upwards.
Introduction
ML Basics
K-nearest Neighbors
The Perceptron
Clustering
Principal Compoent Analysis
MLE & MAP
Naive Bayes
Losgistic Regression
Gradient Descent
Linear Regression
Support Vector Machines
Decision Trees
Boosting
Neural Networks
Convolutional Neural Networks
There will be a number of homework assignments throughout the course, typically made available roughly one to two weeks before the due date. The homework primarily focuses on theoretical aspects of the material and is intended to provide preparation for the exams.
Unless otherwise indicated, you may talk to other students about the homework problems but each student must hand in their own answers and write their own code in the programming part. You also must indicate on each homework with whom you collaborated and cite any other sources you use including Internet websites. Students should never see another student’s solution before submitting their own. Students cannot use old solution sets for this class or solution manual to the textbook under any circumstances. Homework assignments will be submitted through Canvas.
You will have a one-time exemption for a one-day late submission that you can apply to any of your assignments. This will be applied automatically at the end of the semester. The second or subsequent late assignments will be marked as 0 at the end of the semester.
Please submit your homework on time. Homework is worth full credit if submitted before the due date. After the due date, it is worth zero credit, except for the one-time exemption of a one-day late submission. No excuses will be allowed unless you provide an official doctor's note before the deadline and receive my approval.
To provide hands-on learning with the methods discussed in class there are a number of programming projects throughout the course. The projects may be completed individually or in a group of two.
There will be one midterm and one final exam. You are not allowed to discuss them with other people. Missing any exams will automatically result in an F grade.
Tentative Midterm: June 19 at HCB 0212
Tentative Final: July 31 at HCB 0212
There will be extra credit questions on exams and homeworks (CIS 4930 only).
All students are expected to uphold the Academic Honor Code published in The Florida State University Bulletin and the Student Handbook. The Academic Honor System of The Florida State University is based on the premise that each student has the responsibility (1) to uphold the highest standards of academic integrity in the student's own work, (2) to refuse to tolerate violations of academic integrity in the university community, and (3) to foster a high sense of integrity and social responsibility on the part of the university community.
web site for a complete explanation of the Academic Honor Code.
https://fda.fsu.edu/academic-resources/academic-integrity-and-grievances/academic-honor-policy
First Day Attendance Policy: Official university policy is that any student not attending the first class meeting will be automatically dropped from the class.