CSE352/537
Artificial Intelligence
Spring 2022, SUNY Korea
Spring 2022, SUNY Korea
Instructor: Byungkon Kang
Classes: T, Th 09:00 - 10:20 (Zoom link)
Office hours: M, T, Th 14:00 - 15:30 (Same Zoom link as above)
Prerequisite: A grade of 'C' or higher in CSE 216 or 219; CSE Major
This is a course designed to introduce core concepts in artificial intelligence (AI).
We will be studying a variety of topics in AI, with slightly more emphasis on the topics that have become popular recently.
The former includes search, logical inference, and natural language processing (NLP), while the latter includes machine learning, probabilistic inference, and statistical NLP.
By the end of this semester, students are expected to know the following basic ideas:
How to formulate a given problem as a heuristic-based search problem and/or logical inference
How machines achieve generalization via statistical learning
How machines process human-generated natural languages
How machines reason in the presence of uncertainty
Although the official pre-requisite is CSE216, I also recommend that you be familiar with the following topics (or at least be willing to learn them) :
Linear algebra
Probability/statistics
Basic calculus
Feel free to talk to me before registration to find out if this is the right course for you.
Your course will be project-oriented. Please refer to the graduate syllabus for more details.
I will draw materials from the following list of books, although the 'official' book is the first one.
Stuart Russel and Peter Norvig, "Artificial Intelligence: A Modern Approach", Prentice-Hall, 3rd Ed. (AMA)
Kevin P. Murphy, "Machine Learning: A Probabilistic Perspective". The MIT Press. (ML)
Christopher D. Manning and Hinrich Schutze, "Foundations of Statistical Natural Language Processing". The MIT Press. (NLP)
The following may be subject to change, so please check back regularly. You'll need a stonybrook.edu account to access the files.
Week 1: Course overview (courtesy of professor Seungsoo Park) & state space search (2/22, 2/24)
Week 2: Informed search (3/3)
Week 3: Game tree search (3/8, 3/10)
Week 4: Game tree search (3/15), Knowledge representation (3/17)
Week 5: Logical inference (3/22, 3/24)
Week 6: Logical inference (3/29), Midterm 1(3/31)
Week 7: LISP practice (practice code) Proposal due (Graduate students only) (4/5), LISP continued (4/7)
Week 8: Introduction to machine learning + k-NN classification (4/12), Logistic regression (4/14)
Week 9: Decision tree (4/19), Clustering (4/21)
Week 10: Neural networks (4/26), Convolutional neural networks (More deep learning stuff) (4/28)
Week 11: Midterm 2 (5/3) // 5/6: Midterm report due (Graduate students only)
Week 12: Intro. to NLP + Language representation (5/10), Language models (5/12)
Week 14: Intro. to probabilistic reasoning + MLE (5/24), Bayesian networks (5/26)
Week 15: Bayesian networks (5/31), Discussion - Ethical and social issues in AI(6/2)
Week 16: No class (6/7)
Final exam (6/16, 9:00 - 11:30) // Final report due (Graduate students only)
** If you commit an act of academic dishonesty I will make an official report on it. Also, you will be dismissed from the course with a grade of F.**
There will be six (6) homework assignments spanning over all topics.
There will be an in-class midterm during the semester.
Comprehensive, with more emphasis on topics not covered in the midterms.
Up to two (2) excused absences will be overlooked.
You should notify me via a written note (including email) at least two (2) days prior in order to qualify for an excuse.
Valid reasons for an excused absence include, but are not limited to: conference trips, health issues, family affairs.
Missing more than 20 minutes of the class will be considered an unexcused absence. If you have to arrive late or leave early, please let me know in advance.
Students should pursue their academic goals in an honest way that does not put you at an unfair advantage over other students. You are responsible for all work you submitted and representing other’s work as yours is always wrong. Faculty is required to report any suspected instance of academic dishonesty to the school. Regarding your homework, you are encouraged to discuss it with others, but you should write your own code. For more information please refer to http://www.stonybrook.edu/commcms/academic\_integrity/index.html.
If you have a physical, psychological, medical or learning disability that may impact your course work, please let the instructor know. Reasonable accommodation will be provided if necessary and appropriate. All information and documentation are confidential.
Stony Brook University expects students to respect the rights, privileges, and property of other people. Faculty are required to report to the Office of Judicial Affairs any disruptive behavior that interrupts their ability to teach, compromises the safety of the learning environment, or inhibits students' ability to learn. Faculty in the HSC Schools and the School of Medicine are required to follow their school-specific procedures.