CS 441 AML - Applied Machine Learning

Instructor: Prof. Marco Morales Aguirre

Co-Instructor: Dr. Pablo Robles Granda

Course Description

Welcome to Applied Machine Learning. This course is intended for students who want to apply techniques of machine learning to various signal problems. The topics of this course are:

  • Introduction
  • Classification
  • Regression
  • High Dimensional Data
  • Clustering
  • Graphical Models
  • Deep Neural Networks

The course is intended for students who wish to apply machine learning methods with a focus on tool-oriented and problem-oriented exposition. Application areas include computer vision, natural language, interpreting accelerometer data, and understanding audio data.

Prerequisites

A course in probability or statistics, a course in linear algebra, understanding of differentiation and gradients, and some programming experience.

Textbook

The following references are also useful:

  • Kevin P. Murphy, Probabilistic Machine Learning: An Introduction, MIT Press, 2021. You can find it at the author's website
  • Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006

Lecture Videos, Discussion Sessions, and Office Hours

The required video-lectures are designed to discuss the topic for each week and complement the textbook readings and programming assignments. The instructor and co-instructor will hold discussion sessions about the topic of each week, these sessions will not cover material that is not part already of the lecture videos and assignments.

TA Office Hours

The TAs of the course will host office hours via the Zoom teleconferencing software. The currently scheduled office hour times for each staff member will be posted on Coursera. Additional information for logging into the Zoom sessions will be provided on Coursera. Please refer to the reading item about Zoom office hours in Week 1.

Graded work: Programming Assignments and Quizzes

The weekly graded work consists on programming assignments and quizzes. Instructions, and particular submission details and deadlines are published in Coursera. An assignment will clearly state when students should implement an algorithm by hand and the restrictions on the libraries to use.

Submission Procedures

All the quizzes and programming assignments should be submitted on Coursera by their corresponding deadline, which will subsequently be checked and graded.

Exams

This semester of the course does not have any exams, the grading will be based on quizzes and programming assignments.

Campuswire Discussion Forum

The course has a discussion forum on Campuswire where students can post questions and get answers from the teaching assistants and from other students. The staff will address questions in the discussion forum every day during business hours, except on UIUC holidays. When formulating questions, students should follow the guidelines that will be posted in Campuswire.

Students will receive an email invitation once they are added to the class on Campuswire.

Grading, Deadlines, and Late Policy

Students are encouraged to complete each homework in the same week they are assigned in the course. Nevertheless, the deadline for each homework is set a couple of weeks after its corresponding week. Programming assignments and quizzes can be submitted as many times as wanted before the deadline without penalty. The highest grade achieved in assignments and quizzes is kept regardless of the number of times they are submitted.

The individual deadline for each homework is set in Coursera. Assignmens or quizzes submitted after their deadline will have a 2% penalty per day of delay. Nevertheless, students must submit all the required assignments no later than Wednesday, May 4 2022, the last day of instruction. There will be an extra assignment for students eligible to get an A+ whose deadline will be published along with the grading scale.

Students in this course are enrolled for 3 credits or 4 credits. The difference between sections is the required assignments and quizzes as follows:

  • Students in the 4-credit sections (MLG and DSO) should complete all the assignments.
  • Students in the 3-credit section (MLU) should complete all the assignments and quizzes except for the following ones:
    • Assignment 11 Expectation Maximization for Mixture of Normals (in Week 12.)
    • Assignment 12 Mean Field (in Week 13.)

The weights of assignments and quizzes will be shown in Coursera. Please note that the assignment in Week 14 has twice as much weight as those from the rest of the course.

Once the final scores are determined, a grading scale will be determined to assign a letter grade.

Contact Information

Contact Information for the course staff will be posted on the Coursera site. Students are expected to make a good faith effort to research coding questions themselves (referring to documentation, asking on CampusWire) before escalating questions to TA, office hours, and, finally, the professor.

Academic Integrity and Citation Policy

The University of Illinois at Urbana-Champaign Student Code should also be considered as a part of this syllabus. Students should pay particular attention to Article 1, Part 4: Academic Integrity. Read the Code at the following URL: http://studentcode.illinois.edu/.

Academic dishonesty will result in a sanction proportionate to the severity of the infraction, with possible sanctions described in 1-404 of the Student Code (https://studentcode.illinois.edu/article1/part4/1-404/). Every student is expected to review and abide by the Academic Integrity Policy as defined in the Student Code: https://studentcode.illinois.edu/article1/part4/1-401/. As a student, it is your responsibility to refrain from infractions of academic integrity and from any conduct that aids others in such infractions. A short guide to academic integrity issues may be found at https://provost.illinois.edu/policies/policies/academic-integrity/students-quick-reference-guide-to-academic-integrity/. Ignorance of these policies is not an excuse for any academic dishonesty. It is your responsibility to read this policy to avoid any misunderstanding. Do not hesitate to ask the instructor(s) if you are ever in doubt about what constitutes plagiarism, cheating, or any other breach of academic integrity.

In this course, students are allowed to use library code to solve high-level problems, unless an assignment specifically requests that students implement an algorithm completely by themselves. Students should always cite any library code they have used. Students must cite online code references (documentation examples, StackOverflow, Campuswire posts, Slack discussions, etc.) that they have referred to. If students collaborate to any extent, they must cite each other (name and NetID where appropriate) in their code comments. In summary, this policy reflects the University policy on plagiarism as it applies to academic writing.

Students must cite all references, including any code they have used that they did not write themselves. Failure to cite references will be considered an academic integrity violation and be pursued according to University policy, which may include receiving a failing grade on an assignment or in the entire course.

Citations do not need to follow any specific format (such as ACM style, etc.) but should mention the author's name and where the cited work can be found (including a URL, if applicable). In code, a citation can be left in a comment.

Anti-Racism and Inclusivity Statement

The Grainger College of Engineering is committed to the creation of an anti-racist, inclusive community that welcomes diversity along a number of dimensions, including, but not limited to, race, ethnicity and national origins, gender and gender identity, sexuality, disability status, class, age, or religious beliefs. The College recognizes that we are learning together in the midst of the Black Lives Matter movement, that Black, Hispanic, and Indigenous voices and contributions have largely either been excluded from, or not recognized in, science and engineering, and that both overt racism and micro-aggressions threaten the well-being of our students and our university community.

The effectiveness of this course is dependent upon each of us to create a safe and encouraging learning environment that allows for the open exchange of ideas while also ensuring equitable opportunities and respect for all of us. Everyone is expected to help establish and maintain an environment where students, staff, and faculty can contribute without fear of personal ridicule, or intolerant or offensive language. If you witness or experience racism, discrimination, micro-aggressions, or other offensive behavior, you are encouraged to bring this to the attention of the course director if you feel comfortable. You can also report these behaviors to the Bias Assessment and Response Team (BART) (https://bart.illinois.edu/). Based on your report, BART members will follow up and reach out to students to make sure they have the support they need to be healthy and safe. If the reported behavior also violates university policy, staff in the Office for Student Conflict Resolution may respond as well and will take appropriate action.

Statement on CS CARES and CS Values and Code of Conduct

All members of the Illinois Computer Science department - faculty, staff, and students - are expected to adhere to the CS Values and Code of Conduct. The CS CARES Committeeis available to serve as a resource to help people who are concerned about or experience a potential violation of the Code. If you experience such issues, please contact the CS CARES Committee. The Instructors of this course are also available for issues related to this class.

Community of Care

As members of the Illinois community, we each have a responsibility to express care and concern for one another. If you come across a classmate whose behavior concerns you, whether in regards to their well-being or yours, we encourage you to refer this behavior to the Student Assistance Center (217-333-0050 or http://odos.illinois.edu/community-of-care/referral/. Based on your report, the staff in the Student Assistance Center reaches out to students to make sure they have the support they need to be healthy and safe.

Further, we understand the impact that struggles with mental health can have on your experience at Illinois. Significant stress, strained relationships, anxiety, excessive worry, alcohol/drug problems, a loss of motivation, or problems with eating and/or sleeping can all interfere with optimal academic performance. We encourage all students to reach out to talk with someone, and we want to make sure you are aware that you can access mental health support at McKinley Health Center (https://mckinley.illinois.edu/). Or the Counseling Center (https://counselingcenter.illinois.edu/**).**For urgent matters during business hours, no appointment is needed to contact the Counseling Center. For mental health emergencies, you can call 911.

Disruptive Behavior

Behavior that persistently or grossly interferes with classroom activities is considered disruptive behavior and may be subject to disciplinary action. Such behavior inhibits other students' ability to learn and an instructor's ability to teach. A student responsible for disruptive behavior may be required to leave class pending discussion and resolution of the problem and may be reported to the Office for Student Conflict Resolution (https://conflictresolution.illinois.edu; conflictresolution@illinois.edu; 333-3680) for disciplinary action.

Emergency Response Recommendations

Emergency response recommendations can be found at the following website: http://police.illinois.edu/emergency-preparedness/. I encourage you to review this website and the campus building floor plans website within the first 10 days of class. http://police.illinois.edu/emergency-preparedness/building-emergency-action-plans/.

Family Educational Rights and Privacy Act (FERPA)

Any student who has suppressed their directory information pursuant to Family Educational Rights and Privacy Act (FERPA) should self-identify to the instructor to ensure protection of the privacy of their attendance in this course. See https://registrar.illinois.edu/academic-records/ferpa/ for more information on FERPA.

Mental Health

Significant stress, mood changes, excessive worry, substance/alcohol misuse or interferences in eating or sleep can have an impact on academic performance, social development, and emotional wellbeing. The University of Illinois offers a variety of confidential services including individual and group counseling, crisis intervention, psychiatric services, and specialized screenings which are covered through the Student Health Fee. If you or someone you know experiences any of the above mental health concerns, it is strongly encouraged to contact or visit any of the University's resources provided below. Getting help is a smart and courageous thing to do for yourself and for those who care about you.

  • Counseling Center (217) 333-3704
  • McKinley Health Center (217) 333-2700
  • National Suicide Prevention Lifeline (800) 273-8255
  • Rosecrance Crisis Line (217) 359-4141 (available 24/7, 365 days a year)

If you are in immediate danger, call 911 *This statement is approved by the University of Illinois Counseling Center.

Religious Observances

Students should complete the Request for Accommodation for Religious Observances formshould any instructors require an absence letter in order to manage the absence. In order to best facilitate planning and communication between students and faculty, we request that students make requests for absence letters as early as possible in the semester in which the request applies.

Students with Disabilities

To obtain disability-related academic adjustments and/or auxiliary aids, students with disabilities must contact the course instructor and the Disability Resources and Educational Services (DRES) as soon as possible. To contact DRES, you may visit 1207 S. Oak St., Champaign, call 333-4603, e-mail disability@illinois.edu or go to https://www.disability.illinois.edu. If you are concerned you have a disability-related condition that is impacting your academic progress, there are academic screening appointments available that can help diagnosis a previously undiagnosed disability. You may access these by visiting the DRES website and selecting "Request an Academic Screening" at the bottom of the page.

Sexual Misconduct Reporting Obligation

The University of Illinois is committed to combating sexual misconduct. Faculty and staff members are required to report any instances of sexual misconduct to the University's Title IX Office. In turn, an individual with the Title IX Office will provide information about rights and options, including accommodations, support services, the campus disciplinary process, and law enforcement options.

A list of the designated University employees who, as counselors, confidential advisors, and medical professionals, do not have this reporting responsibility and can maintain confidentiality, can be found here: wecare.illinois.edu/resources/students/#confidential.

Other information about resources and reporting is available here: wecare.illinois.edu and wellness.illinois.edu.

Academic Calendar

  • The Graduate College at the University of Illinois maintains a Graduate College calendar. The calendar includes important dates such as final exam dates, course registration and cancellation, and holidays.
  • There is also a campus-wide calendar available.
  • The CS Department also sends reminders about upcoming deadlines. You will also receive the Graduate College newsletter in your Exchange email account.

Course Withdrawal and Refund

For course withdrawal-related questions, please refer to the Academic Calendars. Be sure to select the current term on that page.

This summer course falls under GRAD POT (Part of Term) 1, which is a full 12-week semester course. GRAD POT 1 only refers to summer courses. Spring and fall semester courses do not have multiple sessions.

For course refund information, please refer to the Office of the Registrar refunds website and select the current term. You can also refer to this website for the pro-rate refund schedule if you plan to withdraw from the course after the first day of classes for any given semester.