ISEN 4810 - Special Topics
Fall 2026 Syllabus, Section 01, CRN 43565,
Credit hours: 3
Course Meeting Times
Log in to view more
Instructor
Zefeng Lyu
Email: zlyu@ysu.edu
Course Description
The topic of this offering is Artificial Intelligence for Engineering Applications: Introduction to artificial intelligence methods and their applications across engineering. The course is organized into four modules: machine learning, deep learning, reinforcement learning, and large language models. Engineering data analytics (data wrangling, visualization, and statistical analysis) is integrated throughout as the working foundation of each module. Applications are drawn from across the engineering disciplines, including production scheduling, quality inspection, predictive maintenance, structural health monitoring, load forecasting, fault detection, and process monitoring and optimization. This is a strongly hands-on course: every module pairs projects/mini-projects, and students use Python, Github, and modern AI tools to build, validate, and communicate working solutions. Through module projects and a final project, students are expected to formulate and solve problems drawn from their own engineering background and interests.
Course Readings
| Group | Title | Author | ISBN |
|---|---|---|---|
| No textbook purchase is required |
Lecture notes, Jupyter notebooks, datasets, and tutorials will be provided by the instructor. Each module of the course is supported by a free online textbook and a companion code repository
The course readings are subject to change in the event of extenuating circumstances, research developments, current events, and/or to ensure better learning.
Assignments/Assessments
Log in to view more
Schedule of Topics and Assignments
| Day | Date | Proposed Topic | Due/To Prepare for Class |
|---|---|---|---|
| Tue | 8/25 | Course introduction, toolchain and AI assistants | |
| Thu | 8/27 | Data wrangling and EDA | HW1 assigned |
| Tue | 9/1 | Linear regression and feature engineering | |
| Thu | 9/3 | Model validation I | HW1 due · HW2 assigned |
| Tue | 9/8 | Regularization | |
| Thu | 9/10 | Classification | HW2 due · HW3 assigned |
| Tue | 9/15 | Clustering and dimensionality reduction | Mini-Project 1 assigned |
| Thu | 9/17 | Model validation II | HW3 due |
| Tue | 9/22 | Applications: quality prediction and predictive maintenance | |
| Thu | 9/24 | Module 1 consolidation | Mini-Project 1 due |
| Tue | 9/29 | Neural network fundamentals | |
| Thu | 10/1 | Backpropagation and gradient descent | HW4 assigned |
| Tue | 10/6 | Training loops in practice | |
| Thu | 10/8 | Overfitting and regularization | HW4 due · HW5 assigned |
| Tue | 10/13 | CNN fundamentals and transfer learning | Mini-Project 2 assigned |
| Thu | 10/15 | Sequence models: RNN and LSTM | HW5 due |
| Tue | 10/20 | Applications: visual defect detection and RUL prediction | |
| Thu | 10/22 | MID-TERM EXAM (Modules 1 and 2) | Mid-term Exam |
| Tue | 10/27 | Markov decision processes | Mini-Project 2 due |
| Thu | 10/29 | Q-learning | HW6 assigned · Mini-Project 3 assigned |
| Tue | 11/3 | No Class - INFORMS Conference | |
| Thu | 11/5 | Deep reinforcement learning | HW6 due · HW7 assigned |
| Tue | 11/10 | Applications: scheduling and inventory control | |
| Thu | 11/12 | Module 3 consolidation | HW7 due |
| Tue | 11/17 | Attention, and how large language models work | Mini-Project 3 due |
| Thu | 11/19 | LLM APIs, prompting and structured extraction | HW8 assigned |
| Tue | 11/24 | Retrieval-augmented generation and AI agents | |
| Thu | 11/26 | No Class - Thanksgiving | |
| Tue | 12/1 | Responsible AI and final project work session | HW8 due |
| Thu | 12/3 | Final project presentations | |
| Tue | 12/8 | FINAL EXAM (Modules 3 and 4) | Final report due |
The course schedule, policies, procedures, and assignments in this course are subject to change in the event of extenuating circumstances, by mutual agreement, and/or to ensure better learning.