COSC-3450: Artificial Intelligence

Spring 2026

Contents

• Announcements
• Where, When, Who
• Description
• Learning Goals
• Policies
• CAs, OSs, IDEs, and Tools
• Schedule
• Assignments and Grading
• Materials: Readings, Videos, and Links
• Other Interesting Links

• 4/16/26: Posted the slides for the lecture on k-armed bandits, UCB, MCTS, and AlphaGo.
• 3/31/26: Posted the slides for the lecture on deep neural networks and convolutional networks.
• 4/9/26: Posted p5.
• 3/18/26: Posted p4.
• 2/23/26: Posted p3.
• 2/10/26: Posted hw1.
• 2/3/26: Posted p2.
• 1/29/26: Changed p1's due date to W 2/4.
• 1/14/26: Posted p1. Let the fun begin!
• 1/6/26: Posted the introductory slides on Canvas in the Files section.
• 1/7/26: Posted the date for the final exam: F 5/1 9–11 AM.
• 10/28/25: Posted this Web site.

• Artificial intelligence: A modern approach, 4th Edition, by Russell and Norvig.

My course policies are designed to supplement the University's Undergraduate Honor System and the CS Department's Honor Policy. Unless stated otherwise when I distribute an assignment, the following is the default for all assignments for this course. I have developed my policies from past teaching experiences and from the CS Department's Honor Code at George Mason University.

I am obligated to refer all suspected cases of academic dishonesty by undergraduate and master's students to Georgetown's Honor Council. I am obligated to refer all suspected cases of academic dishonesty by doctoral students to the dean of the Graduate School. If you have any questions about these policies or how they apply, please discuss such concerns with me during class, during office hours, by e-mail, or using the class's discussion board.

Presence

• It is my job to maintain a constructive learning environment for everyone. Please silence your cell phone and other electronic devices. Please do not do work for other classes during our class time.
• The Undergraduate Bulletin stipulates that “[a]ll students are expected to attend all classes...” Your academic work comes first, and you should plan activities so they do not interfere with attending class. If you must miss class for any reason, be sure to get the lecture notes from a classmate. I have detailed more specifics about absences below.
• You must take the final exam with your assigned section and during the period designated by the Registrar.
• If you use your laptop for development, you should make periodic backups of your projects on a university or department machine (e.g., cs-class) so that if something goes wrong with your submission I can verify that you completed the work for an assignment before the deadline.

Academic Integrity

In my experience, students at Georgetown do honest work. The very small percentage of students who have submitted someone else's work as their own did so because they did not manage their time wisely. We now have enough experience and research to show that students who use AI for coursework do not gain domain expertise necessary to ultimately become critical users of AI. This class is where you will continue to learn how to do that. Unless stated otherwise when I distribute an assignment, the following is the default for all assignments for this course.

Citation and Attribution

Students must always follow proper scholarly practice for all submitted work, whether graded or ungraded and whether a draft or final version of a proposal, paper, program, or problem set. As scholars, we must acknowledge our reliance on the work of others through citation. You can never submit someone else's work as your own without proper attribution. If you need assistance with proper citation, please let me know or consult Lauinger Library's Citation Guide.

Indeed, students may be quite adept at and knowledgeable about citing and quoting material from traditional sources, such as books and articles. Typically, we do not have cite facts, common math formulae, or expressions of our own ideas, observations, interpretations, and analyses. However, students new to computer science may not realize that theorems, proofs, algorithms, programs, and code fragments may require the same treatment as any other form of expression.

For convenience, you do not need to cite the course materials, which includes this course webpage, sources linked from this page, the course textbooks, the class lectures and discussion, posts on the discussion board, and conversations with me and the courses assistants. You must, however, cite the use of any resource that is not part of the course materials. Note that “the textbook” does not extend to the textbook's Web site, its contents, lecture slides, solution manuals, code repositories, or any other supplemental material related to the textbook. If you are unsure about what requires citation or what constitutes proper scholarly practice, please ask me during class, during office hours, by e-mail, or using the discussion board.

Permissible Collaboration

I design my courses and assignments so students have what they need to complete the assignments individually without consulting outside resources. The assumption is that all student work is the result of individual effort.

The course assistants and I are available to offer assistance with:

• designing the data structures and algorithms used in your solution;
• implementing your algorithm or data structure in a programming language;
• determining the semantic correctness of your program;
• improving the design of a faulty algorithm or data structure;
• correcting a faulty implementation of an algorithm or data structure;
• designing an experimental study and interpreting its results;
• answering questions you have.

To help you get a sense of what supports your learning and is therefore acceptable, please see the list of potential ways you might seek assistance from a classmate or other person, you can:

• obtain assistance in understanding course materials (textbooks, lecture notes, assignments);
• obtain assistance in learning to use the computing facilities;
• obtain assistance in learning to use special features of a programming language's implementation;
• obtain assistance in determining the syntactic correctness of a particular programming language statement or construct;
• obtain an explanation of a particular syntactic error;
• obtain explanations of compilation or run-time error messages;
• use industry-standard tools for software development that are installed on personal or departmental computers.

Impermissible Collaboration

Because this course forms a part of a sequence and is in service of building your understanding of and agency over fundamental concepts of computer science, you are not allowed to:

• use any external resource or consult with any person outside the course without the proper attribution;
• show or give a copy of your work in any amount or form to another student;
• post course materials or your solutions for any assessment to any site on the Internet, including sites such as GitHub and CourseHero;
• see or receive a copy of someone else's work in any amount or form;
• attempt to gain access to files other than your own or those that I designate and authorize;
• inspect or retain in your possession another student's work, whether it was given to you by another student, it was found after other student discarded his or her work, or it accidentally came into your possession;
• collaborate in any way with someone else in the design, implementation, or logical revision of an algorithm;
• use or present as your own any algorithm, data structure, or implementation that is not of your own or of my design, or that is not part of the course materials without attribution.
• study or incorporate code that others have written, such as code found on the Internet;
• hack the autograder which includes but is not limited to sharing tests and their results with others, and attempting to reverse engineer the routines used for automatic grading.

Copyrighted Materials and Published Work

The materials that I create and use for my courses (“Course Materials”) are my intellectual property. You may not disseminate or reproduce them in any form for public distribution (e.g., sale, exchange, etc.) without my written permission. Course Materials include all written or electronic documents and materials that I provide, including but not limited to syllabi, current and past assessments and their solutions (e.g., exams, homeworks, projects, problem sets, etc.), and presentations such as lectures, videos, slides, etc. Course Materials may only be used by students enrolled in the course for academic (i.e., course-related) purposes. Furthermore, your solutions to assessments are derivative works of my copyrighted material and are therefore subject to that protection because they necessarily incorporate my protected expression. Consequently, you may not further disseminate or reproduce in any form for distribution (e.g., uploading to AI platforms or websites, or offering for sale, exchange, etc.) your solutions to assessments.

Published course readings (book chapters, articles, reports, etc.) available in Canvas are copyrighted material. I make these works available to students through licensed databases or fair use. They are protected by copyright law, and may not be further disseminated or reproduced in any form for distribution (e.g., uploading to websites, sale, exchange, etc.) without permission of the copyright owner. Note that under § 1202 of Title 17 of the U.S. Code it is illegal to remove or alter copyright management information.

You can find more information about intellectual property and copyright here: https://www.library.georgetown.edu/copyright. You can find more information about computer acceptable use policy and intellectual property here: https://security.georgetown.edu/it-policies-procedures/computer-systems-aup.

Copyright issues aside, if you post your solutions to assessments on the Internet, students in current and future classes will be able to find your solutions and submit them as their own work without attribution. Naturally, students who submit another student's work as their own violate my course policies, and in the past, the Honor Council has found these students in violation and sanctioned them. The Honor Council has also found students who post their solutions on the Internet in violation because they facilitated cheating, violated copyright law, the Web site's terms of service, or some combination of these.

I understand that prospective employers may ask for examples of your work. I recommend that students devise a scheme for providing examples in a manner that does not violate copyright law, does not violate the terms of service of the site on which you have posted material protected by copyright, and does not facilitate cheating. One idea is to share a private folder on Google Drive with a prospective employer. Having said this, based on my conversations with students, prospective employers are much more impressed by passion projects of you own design than they are with projects you did for classes.

Deadlines

You must submit all assignments on time. For projects submitted late, there will be a 1% deduction for each minute after the period ends. In the real world, it won't be your grade that decreases. It'll be your stock price.

I grant extensions only to students who have documentation for a medical issue, a family emergency, or an accommodation from the Academic Resource Center. In the cases of a medical issue or a family emergency, you must coordinate with your advising dean since these situations almost always affect your work in all of your classes.

Attendance Details

• You are allowed up to four unexcused absences throughout the course of the semester. If you are absent five or more times, your course grade will be lowered by four percent for the fifth and sixth absences.

• Absences will be excused for participation in a university-sponsored varsity athletics (with confirmation from the appropriate contact) and for religious holidays (for a list of religious holidays that are excused absences, please visit: https://campusministry.georgetown.edu/religious_holy_days.) You are responsible for any material covered during your absence.

• Absences for minor illnesses do not count as excused, but rather count against your four allowed absences. If you will be missing more than two classes because of a serious illness, you must contact your advising dean, who will help you work with all of your professors to formulate a recovery plan. The same goes for other types of emergencies, such as family illnesses. We will deal with such absences in a compassionate way, but since they affect all of your courses, you must work with your advising dean to make a plan for getting back on track.

• Absences due to interviews, employment, and extra-curricular activities do not count as excused.

• In the case of inclement weather that results in the university's closure, we will meet virtually during normal class times using Zoom.

• Programming Projects, 45%
• Project 1, assigned W 1/14, due W 2/4 @ 5 PM ET, 9 points
• Project 2, assigned W 2/3, due F 2/20 @ 5 PM ET, 9 points
• Project 3, assigned R 2/19, due F 3/20 @ 5 PM ET, 9 points
• Project 4, assigned R 3/19, due F 4/10 @ 5 PM ET, 9 points
• Project 5, assigned R 4/9, due T 4/28 @ 11:59 PM ET, 9 points
• Homework (Optional)
• Homework 1
• Midterm Exam, R 2/26, 18%
• Final Exam, F 5/1 9–11 AM, 29%
• Attendance and Participation, 8%

string Grades::getLetterGrade()
{
  if (grade >= 94)
    return "A";
  else if (grade >= 90)
    return "A-";
  else if (grade >= 87)
    return "B+";
  else if (grade >= 84)
    return "B";
  else if (grade >= 80)
    return "B-";
  else if (grade >= 77)
    return "C+";
  else if (grade >= 74)
    return "C";
  else if (grade >= 70)
    return "C-";
  else if (grade >= 67)
    return "D+";
  else if (grade >= 64)
    return "D";
  else
    return "F";
} // Grades::getLetterGrade

I use automatic grading routines to assign an initial grade for the projects. It is important to emphasize that the grade you obtain from Autolab is an initial grade and may not be your final grade. There are many important aspects of a program that are difficult or impossible to assess using automatic grading routines. For example, automatic grading routines can not determine if you have written proper documentation. They can not easily assess if an implementation of an operation is optimally efficient. As a consequence, I start with the initial grade you obtain from Autolab and take further deductions if necessary. I grade the last submission for practical and pedagogical reasons.

For complete implementations, I use the following distribution as a guide:

• 40%: Compiles against the autograder
• 20%: Executes without failure using the autograder
• 40%: Autograder unit tests
• 10%: Internal documentation, if required
• Purpose of classes and methods explained in documentation comments
• Purpose, range, and meaning of identifiers explained, where needed
• Complex flow of control explained
• 10%: Style and formatting
• Nested indentation for loops and conditionals
• All class, method, and function headers emphasized
• Comments set off from code
• Vertical alignment of comments, where appropriate
• White space between blocks of code (and comments)
• Mnemonic identifier names
• 80%: Algorithm and Implementation
• Correct implementation of the operations
• Proper object-oriented design and implementation
• Appropriate error checking and diagnostic messages
• Appropriate data and object types
• Correct, clean, organized output format

Notice that an implementation consisting entirely method stubs would obtain an initial grade of 60%. Such an implementation is incomplete, and would be subject to further deductions based on the effort required to implement the required operations.

In addition to the above, the following deductions may be taken if applicable:

• 20%: Does not compile on cs-class-1
• 1–10%: Incomplete or improper submission
• 1–10%: Debugging or unnecessary output
• 1–5%: My effort for fixing any minor issue
• 1–5%: Inefficiently implemented routine
• 1% per minute: Late deduction

• Autolab, for submitting projects
• Piazza, for online discussions.
• Canvas, for document distribution and submitting projects if Autolab breaks
• ACM's 2013 Curriculum Guidelines for the Intelligent Systems Knowledge Area.
• Dynarski, S. M. (10 August 2017). For better learning in college lectures, lay down the laptop and pick up a pen. Research Report, Brookings Institution, Washington, DC. (Read if interested.)
• Perez-Hernandez, D. (28 March 2014). Taking notes by hand benefits recall, researchers find. The Chronicle of Higher Education. (Read if interested.)
• Mueller, P. A. and Oppenheimer, D. M. (2014). The pen is mightier than the keyboard: Advantages of longhand over laptop note taking. Psychological Science, 25(6):1159–1168. (Read if interested.)
• Russell, S. J. and Norvig, P. (2020). Artificial intelligence: A modern approach, 4th Edition. Prentice-Hall, Upper Saddle River, NJ.
• Russell, S. J. and Norvig, P. (2010). Artificial intelligence: A modern approach, 3rd Edition. Prentice-Hall, Upper Saddle River, NJ.
• AIMA Exercises
• Handout: AI: An Introduction.
• Shein, E. (September 2024). The Impact of AI on Computer Science Education. Communications of the ACM, 67.9: 13–15. (Optional.)
• DeCario, N. and Etzioni, O. (2021). American Needs AI Literacy Now. AI2 Blog. (Optional.)
• Select Committee on Artificial Intelligence (2019). The National Artificial Intelligence Research and Development Strategic Plan: 2019 Update. Networking and Information Technology Research and Development Program. (Optional.)
• Samuelson, P. (July 2023). Legal Challenges to Generative AI, Part I Communications of the ACM, 66.7: 20–23.
• Samuelson, P. (November 2023) Legal Challenges to Generative AI, Part II Communications of the ACM, 66.11: 16–19.
• Video: Self-Driving Car Test: Steve Mahan. (Watch immediately.)
• Video: The Great Robot Race (interesting, but long, so optional)
• Video: IBM's Watson supercomputer destroys all humans in Jeopardy (unrelated to Stanley, but interesting)
• Video: How IBM's Watson supercomputer wins at Jeopardy, with IBM's Dave Gondek (unrelated to Stanley, but interesting)
• Turing, A. (1950). Computing machinery and intelligence. Mind 59(236): 433–460. (Read by midterm.)
• Newell, A., and Simon, H.A. (1976). Computer science as empirical enquiry. Communications of the ACM 19(3): 113–126. (Read by midterm.)
• Barabas, C., et al. (17 July 2019). Technical Flaws of Pretrial Risk Assessments Raise Grave Concerns [Blog post]. Retrieved from https://www.media.mit.edu/posts/algorithmic-risk-assessment/. (Optional.)
• Angwin, J., Larson, J., Mattu, S., and Kirchner, L. (2016). Machine Bias. Propublica. (Optional.)
• O'Neil, C., and Gunn, H. (2020). Near-term artificial intelligence and the ethical matrix. In Liao, S. M. (Ed.). Ethics of Artificial Intelligence, 237–270. Oxford: Oxford University Press. (Read Sections 8.4–8.6 by 4/30.)
• Searle, J.R. (1980). Minds, brains, and programs. Behavioral and Brain Sciences 3(3): 417–457. (Read by 4/30.)
• JASON (2017). Perspectives on Research in Artificial Intelligence and Artificial General Intelligence Relevant to DoD. Technical Report JSR-16-Task-003. The MITRE Corporation, 7515 Colshire Drive, McLean, VA 22102-7508.
• Russell and Norvig's classification algorithms.
• Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM 55(10): 78–87.
• Sutton and Barto's Reinforcement Learning: An Introduction.
• Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. Cambridge, MA: MIT Press.
• Browne, C. et al. (2012). A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games 4(1): 1–43. (optional)
• Wattenberg, Viegas, and Hardt's Attacking discrimination with smarter machine learning.
• Barocas, Hardt, and Narayanan's Fairness and Machine Learning: Limitations and Opportunities.
• Munn, L. (2023). The uselessness of AI ethics. AI and Ethics, 3:869–877.

• Audio/Video: Is the robot rebellion inevitable?
• Video: Self-Driving Car Test: Steve Mahan
• Movie: The Imitation Game
• Article: 'It knew what you were going to do next': AI learns from pro gamers – then crushes them
• Article: Meet Cepheus, the virtually unbeatable poker-playing computer
• Article: Heads-up limit hold'em poker is solved
• Article: Artificial General Intelligence that plays Atari video games: How did DeepMind do it?
• Comic: Tic-Tac-Toe, compliments of Adam Orshefsky
• Comic: Turing Test
• Peet's
• Fast Lane
• Red Bull

Copyright © 2026 Mark Maloof. All Rights Reserved. This material may not be published, broadcast, rewritten, or redistributed.