CSE 5522 Artificial Intelligence II: Advanced Techniques

Advanced concepts, techniques, and applications of artificial intelligence, including knowledge representation, learning, natural language understanding, and vision.

Details
Textbook:
Grading

Grading will be based on:

Participation (10%)

You will receive credit for asking and answering questions related to the homework on Piazza and engaging in class discussion.

Homeworks (50%)

The homeworks will include both written and programming assignments. Homework should be submitted to the Dropbox folder in Carmen by 11:59pm on the day it is due (unless otherwise instructed). Each student will have 3 flexible days to turn in late homework throughout the semester. As an example, you could turn in the first homework 2 days late and the second homework 1 day late without any penalty. After that you will loose 20% for each day the homework is late. Please email your homework to the instructor in case there are any technical issues with submission.

Midterm (20%)

Final Exam (20%)

Regrade Policy: If you believe an error has been made in the grading of your exam, you may resubmit it for a regrade - submit a detailed explanation of which problems you think we marked incorrectly and why. Because we will examine your entire submission in detail, your grade can go up or down as a result of a regrade request.
Grading Scale: Numerical grades will be mapped to letter grades using the standard OSU policy of: 93-100 (A), 90-92.9 (A-), 87-89.9 (B+), 83-86.9 (B), 80-82.9 (B-), 77-79.9 (C+), 73-76.9 (C), 70-72.9 (C-), 67-69.9 (D+), 60-66.9 (D), below 60 (E). These cutoffs represent grade minimums. We may adjust grades upward based on class grade distribution curve.
Drop or Withdraw: detailed OSU policy and instructions here

Resources
  • Piazza (discussion, announcements and restricted resources)
  • Carmen (homework submission)
  • Academic Integrity
    Any assignment or exam that you hand in must be your own work (with the exception of group projects). However, talking with others to better understand the material is strongly encouraged. Copying a solution or letting someone copy your solution is cheating. Everything you hand in must be your own words. Code you hand in must be written by you, with the exception of any code provided as part of the assignment. MOSS (Measure of Software Similarity) will be used routinely to detect plagiarism on programming assignments. Any collaboration during an exam is considered cheating. Any student who is caught cheating will be reported to the Committee on Academic Misconduct. Please don't take a chance - if you are having trouble understanding the material, let us know and we will be happy to help.
    Homework Assignments
  • Homework 0 written part and programming part (due 1/12, hand in a paper copy of both parts at the beginning of class)
  • Programming Project 1 [awards] (due 2/12 - start early!)
  • Programming Project 2 [awards] (due 3/2)
  • Programming Project 3 (due 4/6)
  • Programming Project 4 (due 4/23 - start early!)
  • Excercises
  • Quiz 0 background survey
  • Quiz 1 [solutions] A* Search and Minimax
  • Interactive Practice Alpha-Beta Pruning
  • Quiz 2 [solutions] Markov Decision Processes
  • Quiz 3 [solutions] Reinforcement Learning (Q-learning)
  • Quiz 4 [solutions] Reinforcement Learning (Feature-based Representations)
  • Quiz 5 [solutions] Probability
  • Practice Midterm: [solutions] Search, A* Heuristics, Game Trees, MDPs, Probability (2% bonus credit - if submitted in lecture on 3/2 at 11:10am)
  • Quiz 6 [solutions] Hidden Markov Models
  • Practice Final: [solutions] MDPs, Reinforcement Learning, Markov Model, HMM, Bayes Nets (2% bonus credit - if submitted in lecture on 4/20 at 11:10am)
  • Anonymous Feedback
    Reading Assignments (subject to change as the spring 2018 term progresses.)
    Date Topic Required Reading Suggested Reading
    1/10 Course Overview Russel & Norvig Chapter 1,2
    1/12 Uninformed Search Algorithms and Their Computational Complexity 3.1-3.4
    1/17 Uninformed Search (cont) and Informed Search 3.6 Microsoft Ms. PacMan
    1/19 A* Search, Graph Search and Their Completeness and Optimality 3.5, 3.6 Pancake Sorting
    1/24 Adversarial Search and Intro to Machine Translation 5.1, 5.2, 5.3, 5.4 Machine Translation class and book
    1/26 Expectimax and Utilities 5.5, 13.1, 13.2, 16.1, 16.2, 16.3 Rosen's note on Alpha Beta Pruning
    1/31 Markov Decision Processes and Intro to Robotics 17.1, 17.2
    2/2 Value Iteration and Policy Iteration 17.3 Real-life examples of Markov Decision Processes
    2/7 Reinforcement Learning 1 - Temporal Difference Learning 21.1, 21.2, 21.3 Google AlphaGo
    2/9 Reinforcement Learning 2 - Q-Learning 21.1, 21.2, 21.3
    2/14 Reinforcement Learning 3 - Function Approximation 21.4 Sutten & Barto's new reinforcement learning book (Ch. 5, 6, 13)
    2/16 Reinforcement Learning 4 - Policy Gradient Methods 21.5, 21.6 Deep Q-Learning
    2/21 Probability Review 13.3, 13.4, 13.5, 13.6 Andrew Moore's tutorial and Jean Walrand's note on Probability
    2/23 Guest Lecture by Wuwei Lan (NLP - Semantics/Deep Learning) Wuwei Lan's EMNLP 2017 paper
    2/28 Midterm Review
    3/2 Markov Models 15.1, 15.2
    3/7 Midterm (close book and notes)
    3/9 ~ 3/16 no class (spring break)
    3/21 Markov Models (cont') 15.1, 15.2
    3/23 Guest Lecture by Alan Ritter (NLP - Dialog/Information Extraction) Alan Ritter's publications
    3/28 Hidden Markov Models 1 - Exact Inference 15.1, 15.2
    3/30 Guest Lecture by Peter Massey-Plantinga (Speech/GAN) Baidu's Deep Speech
    4/4 Hidden Markov Models 2 - Approximate Inference, DBNs, Speech Recognition 15.3, 15.5
    4/6 Bayes Nets 1 - Probabilistic Representations 14.1, 14.2
    4/11 Bayes Nets 2 - D-Seperation 14.1, 14.2 Olivier Chapelle's talk on Bayesian Network Click Model for Web Search
    4/13 Bayes Nets 3 - Inference 14.4 David Blei's talk on Topic Models and User Behavior
    4/18 Computer Vision 1 - Applications and CNNs Facebook's Accessibility
    4/20 Final Review, Computer Vision 2 - Visualization 20.1, 20.2.1, 20.2.2 Google's DeepDream
    4/25 (Wed) Final Exam (12:00-1:45pm; close book and notes)