Courses
CAP5610 Introduction to Machine Learning
Course Information
Term: Fall 2025
Class Meeting Days: Monday Wednesday
Class Meeting Time: 09:00AM - 10:15AM
Class Meeting Location: CB1 O220
Credit Hours: 3.00
Instructor: Zhenyi Wang
Office Hours: Monday: 12:00PM - 3:00PM and Wednesday: 12:00PM - 3:00PM
Course Description
CAP 5610 ECS-CS 3(3,0)Machine Learning: PR: CAP 4630 or C.I. Origin/evaluation of machine intelligence; machine learning concepts and their applications in problem solving, planning and expert systems symbolic role of human and computers. Occasional.
This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include supervised learning (parametric/non-parametric algorithms, neural networks), unsupervised learning (clustering, dimensionality reduction), self-supervised learning, out-of-distribution detection, domain adaptation and reinforcement learning. The course will also cover theoretical foundations and recent advances.
Student Learning Outcomes
After successful completion of this course, students will be able to:
Students will understand the mainstream state-of-art machine learning models and algorithms. Proficient in deep learning models and algorithms and know how to effectively train deep neural networks. Present research papers effectively and efficiently. Develop critical thinking skills, know how to analyze the strength and weakness of different machine learning algorithms and how to apply in different learning scenarios.
Course Assessment and Grading Procedure
paper presentation: Each student select one recent paper in machine learning and present it within 12 minutes: 30%. Slides quality 10% and presentation 20%
Three Assignments: 30%. Individual assignment: 10% + 10% + 10%
Mid-term and final exam: 40%. Mid-term exam: 20%; Final exam: 20%
Schedule
| Lecture | Topic | Material | Notes |
|---|---|---|---|
| Lecture 1 | ML history | introduction.pdf | |
| Lecture 2 | Gradient descent, linear and logistic regression | linearregression.pdf | |
| Lecture 3 | Convolutional Neural Network | CNN.pdf | |
| Lecture 4 | Language Model | languagemodel.pdf | |
| Lecture 5 | Transformer and Pre-training | transformerpretrain.pdf | |
| Lecture 6 | Self-superivsed learning I | selfsuperivse1.pdf | |
| Lecture 7 | Self-superivsed learning II | selfsupervise2.pdf | |
| Lecture 8 | Prompting and reasoning | promptreasoning.pdf | |
| Lecture 9 | Instruction tuning and RLHF | InstructionRLHF.pdf | |
| Lecture 10 | Reinforcement learning I | RL1.pdf | |
| Lecture 11 | Reinforcement learning II | RL2.pdf | |
| Lecture 12 | Reinforcement learning III | RL3.pdf | |
| Lecture 13 | Reinforcement learning IV | RL4.pdf |