Basics of Artificial Intelligence
Course Overview
This course is intended for SEAS Engineering graduate students who are interested in understanding the fundamental issues, challenges, and techniques that are associated with recent advances in Artificial Intelligence (AI). The course will discuss the history and properties of basic AI systems, including neural networks, machine learning, and data science, and how to build a basic machine learning and AI project, including data scrapping, data processing, etc. We will discuss the challenges of bias, security, privacy, explainability, ethical issues, and the use of context.
We will learn about AI's use in applications such as image processing and computer vision, natural language processing, recommendation systems, and gaming. The course is supported by a primer on the use of Python to support homework and projects related to machine learning. The course will be a combination of lectures, discussions, activities, and projects that will prepare students without a computer science background to study and apply artificial intelligence tools and applications in a variety of different domains.
Note: The course is NOT intended for students who have a reasonable background in machine learning, computer science, or Python programming. Undergraduates who wish to take this course and petition for credit need to inquire with the SEAS graduate office.
Course Logistics
Course Instructor: Jue Guo
- Research Area: Optimization for machine learning, Adversarial Learning, Continual Learning and Graph Learning
Course Hours: EAS 510LEC - AI1 ; MoWeFr 2:00PM - 2:50PM, Nsc 205
Office Hours: 3:00pm - 4:00pm on Friday
Course Outline
Check out the course material under lecture notes.
| Week(s) | Topics Covered |
|---|---|
| Week 1 and Week 2 | PyTorch Fundamentals & PyTorch Workflow Fundamentals |
| Week 3 and Week 4 | PyTorch Neural Network Classification & Computer Vision |
| Week 5 and Week 6 | Custom Datasets, Going Modular and Transfer Learning |
| Week 7 (One Class) | Midterm (Coverage on Weeks 1, 2, 3, 4, 5) |
| Week 8 and Week 9 | Experiment Tracking & Paper Replicating |
| Week 10, Week 11, Week 12, and Week 13 | Model Deployment |
| Week 14 and Week 15 | Catch up Time on the Material if Needed Final and Review |
Grading
The following is the outline of the grading:
Grading Components
We will have
- Attendance: 10 percent (Random Pop Quiz)
- Programming Assignment: 30 percent (2 PA)
- Midterm: 30 percent
- Final: 30 percent
Grading Rubric
The final grade will be determined based on the overall performance of the class, taking into consideration all relevant assessments and contributions.
- The instructor reserves the right to make final decisions regarding grades.
- Please note that excuses for missed work or poor performance, such as personal conflicts or minor inconveniences, will not be considered unless exceptional and documented circumstances arise.
| Percentage | Letter Grade | Percentage | Letter Grade |
|---|---|---|---|
| 95-100 | A | 70-74 | C+ |
| 90-94 | A- | 65-69 | C |
| 85-89 | B+ | 60-64 | C- |
| 80-84 | B | 55-59 | D |
| 75-79 | B- | 0-54 | F |
Note on Logistics
- A week-ahead notice for mid-term, based on the pace of the course.
- The logistic is subject to change based on the overall pace and the performance of the class.
Lecture Notes
The lecture notes are based on PyTorch documentation and a variety of other resources related to PyTorch. They aim to provide a comprehensive and accessible explanation of key concepts, offering additional insights and examples to enhance understanding.
| Week(s) | Notes |
|---|---|
| Week 1 | PyTorch Fundamentals & PyTorch Workflow Fundamentals |