COSC 4368 --- Fundamentals of Artificial Intelligence Spring 2024 ( Dr. Eick )

Purpose of this Website

• Students who take the undergraduate AI course
• People that want to find out what AI is, what its subfields are, and how its technologies, techniques, and methodlogies can be used in industrial, government, and research-oriented environments.

Basic Course Information

Topics Covered in COSC 4368

Course Materials

Recommended Text:

S. Russell and P. Norvig, Artificial Intelligence, A Modern Approach, Fourth Edition,

Prentice Hall/Allyn&Bacon, December 2020,

Link to Textbook Homepage.

Course Elements

News COSC 4368 Spring 2024

• The classes on April 24 and 29 will discuss belief networks, hidden Markov models, and AI Arms Races. Moreover, the will be a 35 minute review for the May 6 final exam on April 29.
• GHC topics for groups L, O and N have been posted below.
• The midterm exam has been finally graded; its number grade average was 80.11. We apologize for the delay! A link to solution sketches for the midterm exam can be found in the next section, below!

Important 2024 Dates for COSC 4368

Tentative Course Organization

2024 Problem Sets and Group Project

2024 Policies Concerning Late Submissions

2024 Group Homework Credit Tasks

2024 COSC 4368 Polls

Undergraduate Research in Dr. Eick's Research Group

• 2024 Introduction to AI and Course Information COSC 4368 (updated on January 16, 2024; will be used for first two lectures in 2024); see also Dr. Eick's 2019 AI Talk"!
• 2024 Search Transparencies:
  • Search1 (Classification of Search Problems, Terminology, and Overview ), Search2 (Problem Solving Agents), Search3 (Heuristic Search, Exploration and Local Search), Search4 (Randomized Hill Climbing and Backtracking; not covered in textbook), Backtracking Wiki (to be discussed in review for midterm exam), Search5: Games (credit for almost all slides goes to ai.berkely.edu, reduced coverage in 2022), Search5a (Brief Discussion of Bridge and Man vs. Machine Game Contests; not initally covered in 2024), Search6: Constraints Satisfaction Problems (credit for some slides goes to ai.berkeley.edu), Search6a (Dhar & Quale's paper on Dependency Directed Backtracking (DDBT); not covered in 2024), Search7: More on Expansion Search (only material which centers on greedy search and A* will be covered in 2024), Search8 (Kamil on Backtracking; not covered), Suggestions for Solving the Rook+King vs. King Endgame (WRKBK) Problem (not discussed in 2024).
• 2024 Teaching Material on Evolutionary Computing (EC): EC1: Introduction to Evolutionary Computing (by Eiben and Smith covering Chapter 3 of their book) and EC2:Example: Using EC to Solve Travelling Salesman Problems, Eiben-Smith Introduction to EA (they call 'EC': 'EA'!), April 6 EA-paper Walkthrough Notes.
• 2024 Game Theory Slides: G1: Introduction to Gametheory (USC Economics slide show by Shivendra Awasthi (???), will be used in the lecture) and G2: Mo Tanweer Mohammed's Introduction to Game Theory (not used in the COSC 4368 lecture).
• 2024 Machine Learning Coverage:
  • A Gentle Introduction to Machine Learning
  • Reinforcement Learning: RL1 (Introduction to Reinforcment Learning), Deep Reinforcement Learning: Neural Networks for Learning Control Laws (by Steve Brunton; will watch the first six minutes of this video which introduces deep reinforcement learning, and resume watching the video at 13:49 which discusses Alpha-Go and Other Applications of Reinforcement Learning), Reinforcement Learning from Human Feedback: From Zero to ChatGPT (by HugginFace; will just watch 5:50-11:00 of this video which discusses how reinforcement learning is used to train language models, such as GPT), 2019 Soccer RoboCup, Robo Cup, RL2 (Using Reinforcement Learning for Robot Soccer; not covered in 2023), RL3 (Kaelbling's RL Survey Article: particularly, read sections 1, 2, 3, 4.1, 4.2, 8.1 and 9); Steve Brunton's Introductory Video to Reinforcement (might be used in 2024).
  • Introduction to Supervised Learning (also called "Learning from Examples")
  • Neural Networks: Introduction to Neural Networks (covered on March 18, 2024), NN1 (3blue1brown: What is a Neural Network? (suggest you watch this video, if you did not have any exposure to NN before)), Neural Networks (Dr. Eick's "old" 2023 NN slides), NN3 (Russel's Introduction to Neural Networks, not covered in the lecture, but you might take a look at it).
  • Support Vector Machines (not covered in 2024, Review of the SVM lecture).
• 2024 Deep Learning Coverage: Introduction to Generative AI (Google DeepMind Lecture by Ruiqi Gao); Neural Network Basics and Short Introduction to Deep Learning; AutoEncoders (Mahin's March 27, 2024 AutoEncoder Lecture, Mahin's Autoencoder Notebook); Diffusion Models (Lecture (the first 35 slides were covered in the lecture), Demo, ipynb File); Mahin's April 22, 2024 Language Model lecture. The following Deep Learning slide sets were not covered in 2024: Transformers (Transformer Basics); Mahin's April 10, 2023 GPT Overview, Transformer Lab); Convolutional Neural Networks(CNN CNN Article, Second CNN Article, CNN Video for Beginners).
• 2019 Logical Reasoning Transparencies (not covered anymore!):
  • Russel Introduction to First Order Predicate Logic (FOPL) Transparencies (will cover slides 1-11, 13-23 amd 32)
  • Russel Logical Reasoning Transparencies (not used in the lecture).
  • Dr. Eick's Introduction to Resolution and Simple examples of resolution proofs (Asci; helpful for the ProblemSet3 Logical Reasoning Tasks!).
  • Dr. Eick's additional Transparencies Predicate Logic and Resolution(transparencies 1, 2 and 4 will be covered in 2019!).
• 2024 Reasoning in Uncertain Environments Transparencies
  • Review Probability Theory
  • Naive Bayesian Approaches: Bayes' Theorem" and Naive Bayes Classifiers(not covered in 2023) (Wikipedia NBC Reading Material(not covered in 2023)
  • Belief Networks: UC Berkeley's Introduction to Belief Networks (not covered) and Dr. Eick's Computations in Belief Networks (to be covered in the lecture) Transparencies; Russel's Inference with Belief Networks Transparencies (will not be covered in the lecture, but give a good survey on different implementation stategies for belief networks); Lesser's Introduction to Belief Networks(explains d-separation quite well, but will not be used in the lecture).
  • Hidden Markov Models: ai.berkeley.edu's Markovian Decision Processes not covered in 2023, Daphne Koller's Introduction to Hidden Markov Models Video covered in 2023, Dr. Eick's Hidden Markov Model Slides only partially covered in 2023, How does the Viterbi Algorithm Work Video not covered in 2023
• 2024 Societal and Ethical Issues of AI and AI Politics
  • Organization of this Part of the Course and Discussion Questions about some of the Videos Listed Below (will be discussed in class!)
  • AI FOR GOOD - Ethics in AI (a video discussing how to incorperate ethics into AI systems; might or might not be covered in 2023)
  • MIT to Spend $1 Billion on Program to Study AI Ethics (watch the video inside this webpage)
  • Human Do not Need to Apply (a video that analyzes the influence of AI on jobs)
  • Top Ten Ethical Issues in AI
  • European Effort to Regulate AI (from 2021)
  • European Commission Ethics Guidelines for "Trust-worthy" AI
  • AI's Impact on Society (watch starting 12:19 skip to 18:00 centering on fake news and autonnomuous weapons and 28:00 Chinese AI and 38:00 for AI and kids)
  • Courses and Institutes which focus on ethical and societal aspects of AI: Geogia Tech, Stanford 1, Stanford 2, MIT, Havard.
  • Plato.stanford.edu: Ethics for AI and Robotics, Coscra Ethics for AI lecture".
• 2020 Planning Slides: Introduction to Planning (based on a lecture by Jim Blythe, Jose Luis Ambite,Yolanda Gil; likely not covered in 2024)
• 2017 Last Words
• 2006/2009 Soft Computing Transparencies
  • Zadeh's Definition of Soft Computing
  • Introduction to Soft Computing (just print out the first 3 pages of the pdf-file that will be used in the lecture)
  • Fuzzy Sets (just look at the first 2 transparencies)
• A quick look to Knowledge-based Systems
• Foundations of AI (quite short; to be discussed in the last class of the semester)
• 2009: Topics covered and not covered in COSC 6368.
• Dec. 7, 2004 Review for the final exam;

2024 Lecture Attendance

Old 2024 News Items

• The group project's submission deadline has been extended and finalized to Su., April 14; groups with 3 members (due to dropping of a group member) get 2 extra days.
• Optional GHC Task: Overview about Techniques, Algorithms, and Frameworks used in the AlphaGo Program (to be presented on April 15; Silver's AlphaGo Nature Paper; Video about the AlphaGo Paper.) Groups K, L, M, N and O: If you like to present this topic (as your GHC Task) send Dr. Eick an e-mail by March 31 the latest!
• Please Dr. Eick or the course TAs via e-mail, rather using MS Teams; especially, if in more important cases.
• Currently, you mostly see the course website of the Spring 2023 teaching of this course; this website will be updated incrementally as we move along with teaching the course in Spring 2024. The course topics covered in Spring 2024 will not be significantly different from those covered in Spring 2023; however, we will be covering two new deep learning topics: diffusion models and convolutional neural networks (CNN), centering on U-Net. Moreover, we will discuss language models at a non-technical level in 2024, centering on what they are and what they can be used for.
• The course will use MS Teams called "H_20241_COSC_4368_12510" to managage assignment submission, for managing and displaying grades and as a chat platform. There seem to be at the moment some technical difficulties with adding enrolled students to this team. However, if you are not enrolled in this team by Monday, January 22 end of the day, contact the course TAs or Dr. Eick to add you manually to this team!

Reinforcement Learning Videos

Prerequisites

Other Matial Related to COSC 4368

2002 Exam Solution Sketches

Grading

Only machine written solutions to homeworks and project reports are accepted. Be aware of the fact that our only source of information is what you have turned in. If we are not capable to understand your approach or solution, you will receive a low score. Moreover, students should not throw away returned assignments or tests.

Students may discuss course material and homeworks, but must take special care to discern the difference between collaborating in order to increase understanding of course materials and collaborating on the homework / course project itself. We encourage students to help each other understand course material to clarify the meaning of homework problems or to discuss problem-solving strategies, but it is not permissible for one student to help or be helped by another student in working through homework problems and in the course project. If, in discussing course materials and problems, students believe that their like-mindedness from such discussions could be construed as collaboration on their assignments, students must cite each other, briefly explaining the extent of their collaboration. Any assistance that is not given proper citation may be considered a violation of the Honor Code, and might result in grade reduction, obtaining a grade of F in the course, and in further prosecution.

2020 Reviews and Exams

2021 Final Exam and Review for it

2023 Problem Sets and Group Project

2023 Group Homework Credit Tasks

Miscellaneous