COSC-288: Introduction to Machine Learning

Fall 2022

Contents

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

• 11/19/22: Posted p5.
• 11/15/22: Poslted slides for deep learning, reinforcement learning, and big data. You can also find this file on Canvas in the Files section.
• 11/19/22: Posted the room for the final exam: WAL 398, our classroom.
• 11/2/22: Posted p4.
• 10/5/22: Posted p3.
• 9/14/22: Posted p2.
• 8/24/22: Posted p1. Let the fun begin!
• 7/30/22: Published this Web site.

• A Course in Machine Learning, by Hal Daumé III

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.

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.

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. The University assumes that students learned how to properly cite material at their previous institutions. If this is not the case, please let me know.

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 the syllabus, sources linked from the syllabus, the course textbook, the class lectures and discussion, posts on the discussion board, and conversations with me and 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 material related to the textbook. The syllabus links to any such material pertinent for the class. 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.

I design my courses and assignments so students have what they need to complete the assignments individually without consulting outside resources. I determine the size of and credit for assignments based on the assumption that the work for them is the result of individual effort using only the course resources and materials. Students who use outside resources to complete assignments may not be eligible for full credit. Students who do not acknowledge their use of outside resources to complete assignments may be in violation of my course policies and the university's policies on academic integrity.

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 websites, 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.

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, it is possible that students in future classes will find your solutions and submit them as their own work without attribution. Naturally, students who do so violate my course policies, and the Honor Council will with high probability find them in violation and sanction them. The Honor Council may also find you in violation because you facilitated cheating and violated copyright law and the Web site's terms of service.

I understand that it is often important for securing a job or an internship for students to provide prospective employers with a portfolio of their work. I recommend that students devise a scheme for doing so 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.

The following list details acceptable and unacceptable practices:

• 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.
• You can obtain assistance only from me and the course assistants:
  • in designing the data structures and algorithms used in your solution;
  • in modifying the design of an algorithm or data structure determined to be faulty;
  • in implementing your algorithm or data structure in a programming language;
  • in correcting a faulty implementation of your algorithm or data structure;
  • in determining the semantic correctness of your program;
  • in designing an experimental study and interpreting its results.
• You can not:
  • 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.
  • 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.

Policies dealing logistics:

• You have permission to occasionally take digital photos of the material on the board for your personal and course-related use, but you can not post these recordings on the Internet. It is important to understand that all of the course material is covered by copyright, either mine or someone else's.
• You should submit all assignments on time. For late projects, there will be a 1% deduction for each minute after the deadline. 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, it would be best to coordinate with your advising dean since these situations often affect your work in all of your classes.
• If you use your laptop for development, you should keep a backup 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.
• You must take the final exam with the section and during the period designated by the Registrar.
• It is my job to maintain a constructive learning environment for everyone. Please silence your cell phone and other electronic devices.
• The University and I expect you to attend all classes. If you must miss class, be sure to get the lecture notes from a classmate.
• It is fine if you must leave class early, arrive late, or leave the room to answer your phone, but you should do so in a manner that does not disturb your fellow students.
• In the case of inclement weather that results in the university's closure, we will meet virtually during normal class times using Zoom.
• The Undergraduate Bulletin stipulates that “[a]ll students are expected to attend all classes...” Furthermore, in the classroom, I value and promote questions and discussions. It is important for all students to hear and learn from these discussions even if they choose not to participate. As a consequence, you will be allowed up to three unexcused absences throughout the course of the semester. If you are absent four or more times, your course grade will be lowered by one unit for each absence after the third (e.g. A to A- for the fourth absence, A- to B+ for the fifth).

  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 three allowed absences. If you will be missing more than two classes because of a serious illness or because you have been asked to quarantine, you should 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 will work with your advising dean to make a plan for getting back on track.

  Finally, if you must miss class for any reason, be sure to get the lecture notes from a classmate.

1. Introduction: Definitions, Areas, History, Paradigms [ciml ch 1; ciml ch 2]
2. Instance-based learning: k-NN [ciml ch 3]
3. Probabilistic learning: Probability review, Bayes' Theorem, naive Bayes [ciml § 9.3]
4. Evaluation: Train/Test Methodologies, Measures, ROC Analysis [ciml ch 5; PFK 98; F 06]
5. Decision Trees: ID3, C4.5, Stumps [ciml ch 1]
6. Midterm Exam
7. Neural Networks: Linear classifiers, Perceptron [ciml ch 4; § 7.1–7.4;]
8. Neural Networks: Multilayer networks, Back-propagation [ciml ch 10]
9. Support Vector Machines: Perceptron, Dual representation [ciml § 7.7; ch 11]
10. Support Vector Machines: Margins, Kernels, Training, SMO [ciml ch 11]
11. Ensemble Methods: Bagging, Boosting [ciml ch 13]
12. Ensemble Methods: Random Forests, Voting, Weighting
13. Ethics, Bias, and Fairness [ciml ch 8; Mehrabi et al. (2019)]

• Programming Projects, 45%
• Project 1, assigned W 8/31, due F 9/16 @ 5 PM ET, 9 points
• Project 2, assigned R 9/15, due F 10/7 @ 5 PM ET, 9 points
• Project 3, assigned R 10/6, due F 11/4 @ 5 PM ET, 9 points
• Project 4, assigned R 11/3, due W 11/23 @ 11:59 PM ET, 9 points
• Project 5, assigned T 11/22, due T 12/6 @ 11:59 PM ET, 9 points
• Midterm Exam, R 10/13, 18%
• Final Exam, Sa 12/10 12:30–2:30 PM ET, WAL 398, 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 pedgagical 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 discussion
• Canvas, for document distribution and for submitting projects if Autolab is down
• 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.)
• Flach, P. (2012). Machine learning: The art and science of algorithms that make sense of data. Cambridge University Press, Cambridge.
• Mitchell, T. M. (1997). Machine learning. McGraw-Hill, New York, NY.
• Daumé III;, H. (2017). A course in machine learning
• Shalev-Shwartz, S. and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, Cambridge.
• Murphy, K. P. (2012). Machine learning: A probabilistic perspective [electronic resource]. MIT Press, Cambridge, MA.
• Gomes, L. (20 Oct 2014). Machine-learning maestro Michael Jordan on the delusions of Big Data and other huge engineering efforts. IEEE Spectrum.
• Ramirez, E. et al. (2016) Big data: A tool for inclusion or exclusion? — Understanding the issues FTC Report. Federal Trade Commission: Washington, DC.
• Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM 55(10): 78–87.
• 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.
• Provost, F., Fawcett, T., and Kohavi, R. (1998). The case against accuracy estimation for comparing induction algorithms. In Proceedings of the Fifteenth International Conference on Machine Learning, 445–453. Morgan Kaufmann, San Francisco, CA.
• Fawcett, R. (2006). An introduction to ROC analysis. Pattern Recognition Letters 27(8): 859–928.
• Domingos, P. and Hulten, G. (2000). Mining high-speed data streams. In Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 71–80. ACM Press, New York, NY.
• Cohen, W. W. (1995). Fast effective rule induction. In Proceedings of the Twelfth International Conference on Machine Learning, 115–123. Morgan Kaufmann, San Francisco, CA.
• Saltz, J., Skirpan, M., Fiesler, C., Gorelick, M., Yeh, T., Heckman, R., Dewar, N., and Beard, N. (2019). Integrating Ethics within Machine Learning Courses. ACM Transactions on Computing Education 19(4), Article 32, 26 pages.
• Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., and Galstyan, A. (2019). A survey on bias and fairness in machine learning. arXiv.

• Google Scholar

• Blog post: Practical Advice for Building Deep Neural Networks
• Article: A visual introduction to machine learning
• Article: Meet Cepheus, the virtually unbeatable poker-playing computer
• Article: Heads-up limit hold'em poker is solved
• Survey: Research Leaders on Data Mining, Data Science, and Big Data key trends, top papers
• Radio broadcast episode: Why machines discriminate—and how to fix them Science Friday, 11/20/2015.

Copyright © 2022 Mark Maloof. All Rights Reserved. This material may not be published, broadcast, rewritten, or redistributed.