Description
Artificial intelligence (AI) has become increasingly important in the modern world. Search engines, video games, financial algorithms, and autonomous vehicles all use AI to provide useful services. Boston Dynamic, Alpha Go (which beat the number one Go player in the world), SIRI, OpenAI Five (which beat Dota 2 world champions), Google, Facebook’s recommendation system and many other advanced applications benefit from using AI. This course provides an introduction to the theory and approaches in AI. You will learn the foundational principles that drive these applications and practice implementing some of these systems yourselves.
Syllabus
Date | Lecture Topic | Recommended Reading | Quiz | Project |
---|---|---|---|---|
May 29 | Introduction to Artificial Intelligence | Russell & Norvig (RN) Ch. 2 | Quiz 0 UBLearns -> Assignments Due Sunday @11:59pm |
None |
Course Logistics | ||||
Inteligent Agents | ||||
Search | ||||
June 3 | Uninformed Search (BFS, DFS, UCS) | RN Ch. 3 | Quiz 1 | None |
Informed Search (Greedy, A*) | ||||
Python/Google Colab overview | June 5 | Informed Search | RN Ch. 3.5-3.6, 5.1-5.3 | Quiz 1 | None |
Adversarial Search Game Trees | ||||
[Recitation] Probabilities Intro | June 10 | Uncertanty and Probability | RN Ch. 13.1-5, 14.1-2,4 | Quiz 2 |
Project 1
UBLearns > Assignments |
Bayesian Networks: Representation | ||||
[Recitation] Bayes’ Nets Examples | June 12 | Bayesian Networks: Inference | RN Ch. 14, 15.1-15.3 | Quiz 2 | Project 1 Due Sunday @11:59pm |
Bayesian Networks: Sampling | ||||
Hidden Markov Models | ||||
[Recitation] Markov Chain/HMM Examples | June 17 | Reinforcement learning (RL): Basics | - SB (Sutton and Barton) Ch. 3
- David Silver's course on Reiforcement Learning |
Quiz 3
Release |
Project 2
Release |
Defining RL and Markov Decision Process | ||||
Polices, Value Functions & Bellman Equations | ||||
[Recitation] Gym environments basics Demo | June 19 | Model-based RL: Dynamic Programming | - SB (Sutton and Barton) Ch. 4, 5.1-5.4, 6.1-6.5 |
Quiz 3
|
Project 2
|
Model-Free RL: Monte Carlo and Temporal Difference | ||||
Learning and planning | ||||
Q-Learning Demo | ||||
[Recitation] Q-Learning | June 24 | Learning and planning: Model Free Solutions | - SB (Sutton and Barton) Ch. 5-6 |
Quiz 4
Release |
Project 2 Due Thursday @11:59pm |
Q-Learning Review | ||||
[Recitation] Solving Q-Learning | June 26 | Reinforcement Learning: Recap | None |
Quiz 4
Release |
Project 3 Release |
Safety in AI | ||||
Course Material Review | ||||
July 1 | Fake Art Competion Results | None | None |
Project 3 Due Monday @1 pm |
Students Projects Presentations | ||||
Q&A before Final | ||||
July 3 | Final | None | None | None |
Logistics
- Instructor: Alina Vereshchaka
- Session: May 28 - Jul 05
- Lectures: Mon/Wed 2:00 - 5:15pm, Bell 138
- Recitations: Mon/Wed 5:15 - 6:15pm, Bell 138
- Office hours: Mon/Wed 12:30 - 1:30pm, Tue/Thu 1:30 - 2:30pm
Competition
- Competion decricrition (pdf)
- Important Date: Due date is on June 28
- Important Date: Presentation is on July 1
Calendar
Add our schedule to your calendar here.Reference Materials
Our main book:- Artificial Intelligence: A Modern Approach (3rd Edition) by Stuart Russell, Peter Norvig
- Lecture slides and other relevant Materials will be added
- Richard S. Sutton and Andrew G. Barto, "Reinforcement learning: An introduction", Second Edition, MIT Press, 2019 - is a classical book and covers all the basics
- David Silver's course on Reiforcement Learning
Useful Materials:
- Interactive Python tutorial Learn Python
- Probabilities overview
Evaluation
- 50% - Projects (3 projects: 15 + 15 + 20)
- 20% - Short weekly quizzes
- 30% - Final Exam
Late Day Policy
- You can use up to 3 late days
- A late day extend the deadline by 24 hours
- If you have more then 3 days after the deadline, a penalty of 25% for one day will be applied any work submitted after the that time.
Office hours and recitations
- Office hours and recitations start from Monday, June 3
- Office hours are held in Davis Hall
- Recitations are held in Bell 138
- Office Hours can be held in person or online. For online office hours, you will need to create a Google Hangout event and invite me (avereshc[at]buffalo.edu)
Weekly Quizes - How does it work?
- Released every Monday 9am, due by Sunday 11:59pm
- Can be found at UBlearns > Assignments
- Each quiz will contain 4-5 problems on topics covered that week
- At the end of a submission, the system will give you your final score
- 5 quizzes in total, only 4 quizzes with the highest scores will be counted
- Three attempts allowed, only the highest score will be kept
I want to become a Rockstart in AI, what are the good resources to start?
- Machine Learning Crash Course with TensorFlow APIs - thanks to Nickson for reference!
FAQ
When is the final?
Final examination is sheduled on the last day of our class (July 3)
What do I need to do before class starts?
- Sign-up for Piazza (if you do not have an account already) and enroll into the CSE 368 Introduction to Artificial Intelligence class.
- Confirm that the class shows up in your UBLearns account.
What programming language will be used?
We will be using Python as the programming language for the projects.
Attendance
Attendance is not required but is encouraged. Sometimes we may do in class exercises or discussions related to quizes or projects and these are harder to do and benefit from by yourself
I am highly interested in the course, but I cannot register, can I attend?
Yes, you are welcome to audit the course.