CS4804 Fall 2022
This course will introduce the foundations of modern artificial intelligence (AI) and key ideas and techniques underlying the design of intelligent computer systems. It will focus on concepts that are not only important in the space of AI but are also practically useful in modern applications. We will practice effective methods of reasoning about AI problems, which will generalize beyond the specific topics we study in class. Topics include (but are not limited to) search, game playing, logic, machine learning, deep learning, natural language processing, robotics and image processing. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue.
| Mon. | Tue. | Wed. | Thu. | Fri. |
|
TA office hours: Chiawei Tang 2:00 - 4:00 PM |
TA office hours: Ming Zhu 1:00 - 3:00 PM Class: SURGE 104A 3:30 PM - 4:45 PM |
TA office hours: Chiawei Tang 2:00 - 4:00 PM |
TA office hours: Ming Zhu 1:00 - 3:00 PM Class: SURGE 104A 3:30 PM - 4:45 PM |
Instructor office hours: Yinlin Chen 10:00 - 11:00 AM |
Blacksburg campus:
https://canvas.vt.edu/courses/156167
The only official prerequisite is CS 3114 (Undergraduate Data Structures and Algorithms). You should be comfortable with discrete mathematics, basic probability and statistics, basic logic, computational complexity, data structures, and algorithm analysis. The homework assignments will include programming portions using Python.
Please speak with the instructor if you are concerned about your background.
| Week | Dates | Tue | Thur | Notes |
|---|---|---|---|---|
| 1 | 08/22-08/26 | Overview of AI Ch.1 |
Agents / Python & Projec 0 Ch.2 |
Project 0: Tutorial |
| 2 | 08/29-09/02 | Uninformed Search Ch. 3.1 – 3.4 |
Informed Search Ch. 3.5 – 3.6 |
HW 1 / Project 1: search |
| 3 | 09/05-09/09 |
Game, Adversarial Search Ch. 5.1 – 5.3 |
Game, Adversarial Search Ch. 5.1 – 5.3 |
|
| 4 | 09/12-09/16 | Game, Expectimax, Utilities Ch. 5.5 & 16.1 – 16.3 |
Probability Ch. 12.1 – 12.5 |
HW 2 / Project 2: Game |
| 5 | 09/19-09/23 | Constraint satisfaction problem (CSP) I Ch. 6.1 – 6.2 |
University Closed | |
| 6 | 09/26-09/30 | CSP II Ch. 6.3 – 6.5 |
Propositional Logic Ch. 7.1 – 7.5 |
HW 3 |
| 7 | 10/03-10/07 | Markov Decision Processes (MDP) Ch. 17.1 – 17.3 |
MDP II Ch. 17.3 – 17.5 Machine Learning Fundamentals. Ch. 19 |
|
| 8 | 10/10-10/14 | Reinforcement Learning I Ch. 22.1 – 22.2 |
Midterm (3:30 pm – 4:45 pm) |
HW4 |
| 9 | 10/17-10/21 | Reinforcement Learning II Ch. 22.3 – 22.5 Mini-Project |
Bayesian Networks I Ch. 13.1 – 13.3 |
Project 3: Reinforcement Learning |
| 10 | 10/24-10/28 | Bayesian Networks II Ch. 13.3 – 13.5 |
Decision Networks / HMMs Ch. 14.1 – 14.3 & 16.5 – 16.6 |
HW5 |
| 11 | 10/31-11/04 | Particle Filters Ch. 14.1 – 3,14.5 |
Machine Learning,Decision Tree, Naïve Bayes, Perceptron Ch. 20 |
HW 6 / Project 4: Ghostbusters |
| 12 | 11/07-11/11 | Deep Learning Fundamentals Ch. 21.1-21.2 |
Deep Learning & Neural Networks Ch. 21.3 – 21.6 |
HW 7 |
| 13 | 11/14-11/18 | Deep Learning for Nature Language Processing |
AI application & Research / The Ethics of AI |
HW 8 / Project 5: Machine Learning |
| 14 | 11/21-11/25 | No class |
No class |
Thanksgiving break |
| 15 | 11/28-12/02 | Mini-Project Presentation |
Mini-Project Presentation / Semester recap |
|
| 16 | 12/05-12/09 | No class |
Reading Day |
12/09 (Fri) Final Exam 10:05 am – 12:05 pm |
Around the midterm week, students will start to work on small AI/ML projects in groups of 2 - 4 students. The goal of the mini-project is for students to use techniques learned from this class with supplemental materials to gain practical AI experience.
Requests for regrading due to grading errors must be submitted in writing to a TA within one week of the release of grades.
Homework & project assignment submitted late without permission will be penalized according to the following formula:
(Penalized score) = (Your raw score) * (1 - 0.1 * (# of days past deadline))
This formula will apply for up to three days, after which the homework will not be accepted and you will receive a grade of zero. Avoid invoking these penalties by starting early and seeking extra help.
Based on the grading breakdown above, each student's final grade for the course will be determined by the final percentage of points earned. The grade ranges are as follows:
| A | 93.3%–100% | A- | 90.0%–93.3% | B+ | 86.6%–90.0% | B | 83.3%–86.6% |
| B- | 80.0%–83.3% | C+ | 76.6%–80.0% | C | 73.3%–76.6% | C- | 70.0%–73.3% |
| D+ | 66.6%–70.0% | D | 63.3%–66.6% | D- | 60.0%–63.3% | F | 00.0%–60.0% |
The Graduate Honor Code pledge that each member of the university community agrees to abide by states: "As a Hokie, I will conduct myself with honor and integrity at all times. I will not lie, cheat, or steal, nor will I accept the actions of those who do."
Students enrolled in this course are responsible for abiding by the Honor Code. A student who has doubts about how the Honor Code applies to any assignment is responsible for obtaining specific guidance from the course instructor before submitting the assignment for evaluation. Ignorance of the rules does not exclude any member of the University community from the requirements and expectations of the Honor Code. For additional information about the Honor Code, please visit: https://graduateschool.vt.edu/academics/expectations/graduate-honor-system.html
This course will have a zero-tolerance philosophy regarding plagiarism or other forms of cheating. Your assignments must be your own work, and any external source of code, ideas, or language must be cited to give credit to the original source. I will not hesitate to report incidents of academic dishonesty to the Office of the Graduate Honor System.
Because the course will include in-class discussions, we will adhere to Virginia Tech's Principles of Community. The first two principles are most relevant:
The remaining principles are also important and we will take them seriously as a class.