Course Logistics
IDS:705 Principles of Machine Learning
- When: Tuesday and Thursdays 10:05am - 11:20am
- Where: Gross Hall 103
Class Tools and Resources
- Ed Discussions: Announcements, Q&A on course content (assignments, quizzes, grades), ALL course communications
- Gradescope: Quizzes, assignments, and project submission & feedback
- Schedule: Schedule of class topics and deliverables
- Canvas: Posted grades
Textbooks
A version of each book is available free online:
- An Introduction to Statistical Learning with Python by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani, 2013.
- Understanding Deep learning by Simon Prince, 2023.
- Pattern Recognition and Machine Learning by Christopher Bishop, 2006.
- Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, 2016.
- Reinforcement Learning: An Introduction, by Richard Sutton and Andrew Barto, 2018.
Assignments & Grading
Assignments, projects, & quizzes: Assignments and projects details are posted on the course syllabus. For expectations and instructions on the assignments, see the assignment instructions. Quizzes are found on Gradescope and are due prior to the start of the lecture for which they’re titled (i.e. the Lecture 3 Quiz is due by the start of Lecture 3).
Grading:
- 60% Assignments (5, each worth 12%)
- 25% Quizzes (~23, each worth ~1%)
- 15% Final Project
Prerequisites
This course moves quickly, so having a firm grasp on prerequisites is important. The prerequisites are as follows:
- Programming: Fundamentals of Python programming.
- Mathematics: Calculus and linear algebra.
- Statistics: Introductory probability and statistics.
Course Policies
Academic dishonesty
Adherence to the Duke Community Standard is expected. To uphold the Duke Community Standard:
I will not lie, cheat, or steal in my academic endeavors;
I will conduct myself honorably in all my endeavors; and
I will act if the Standard is compromised
Anyone found in violation of the Standard will be reported to the Office of Student Conduct.
Class Attendance
Attending class is a vital component of the course as it is one of the multiple ways in which you will interact with and learn course material. In person class attendance is therefore expected for this course. For any special circumstances, please reach out to the course instructor.
Sick absences
To keep the university community as safe and healthy as possible, please do not come to class if you have cold symptoms. Please inform me of your absence and plan to complete any missed work. Students who encounter short- and long-term medical issues or instances of personal distress or emergency can seek academic support if needed. Recordings of the class will be available for excused absences.
Accommodations and accessibility
If you need special accommodations due to physical or learning disabilities, medical needs, religious practices, or other reasons, please inform us as soon as possible so we can work to accommodate those needs.
If you are a student with a disability and need accommodations for this class, please register with the Student Disability Access Office (SDAO) and provide them with documentation of your disability. SDAO will work with you to determine what accommodations are appropriate for your situation. Please note that accommodations are not retroactive and disability accommodations cannot be provided until a Faculty Accommodation Letter has been given to your instructor. Please contact SDAO for more information: sdao@duke.edu or .
Late Submissions
Assignments and projects are due in class by the start of class on the date posted. Late deliverables will ONLY be accepted at the discretion of the instructor and according to the following:
- Course projects deliverables will not be accepted after the deadline.
- Late assignment submissions will result in a reduction of 5 points off the grade per day late.
- Quizzes will not be accepted after the deadline since the answers to the quizzes are discussed in and made available after the class in which they’re due. Quizzes are typically posted a week or more in advance, so you are encouraged to start early (you can submit as early as you’d like). Quizzes cannot be made up, but there will be an opportunity later in the semester to make up a quiz to account for any off days.
Please reach out to the TA’s or instructor as early as possible to request any special accommodations.
Collaboration
There will be three modes of collaboration ranging from fully-collaborative group projects, to fully-independent work. The three modes are as follows, and will be indicated throughout the course:
- Mode 1: Team-based Assignment. Collaboration is expected with every member of the team contributing to a single deliverable. Applies to the Project
- Mode 2: Individual Assignment – Collaboration Permitted. Students hand in individual work, but they may work with others if they provide citations of the help they received, such as a list of people who assisted/collaborated with them to produce the final product. Duplication or copying is not permissible, even in part, and constitutes a breach of the honor code. Applies to Assignments
- Mode 3: Individual Assignment – No Collaboration Permitted. Students hand in individual work that is completed entirely independent of any discussion or help from other students. Clarifying questions to teaching assistants and instructors are both permissible and encouraged. Applies to Quizzes
Rules for recording course content
Student recording recordings of lectures must be permitted by the instructor prior to recording and shall be for private study only. Such recordings shall not be distributed to anyone without authorization by the instructor whose lecture has been recorded. However, the instructor may arrange through the Office of Information Technology to make recorded lectures available to students enrolled in the class on such terms and conditions as he or she prescribes. Redistribution of recorded lectures is prohibited. Unauthorized distribution is a cause for disciplinary action by the Judicial Board. The full policy on recoding of lectures falls under the Duke University Policy on Intellectual Property Rights, available here.
Mental Health and Wellness Resources
Student mental health and wellness are of primary importance at Duke, and the university offers resources to support students in managing daily stress and self- care.
If your mental health concerns or stressful events negatively affect your daily emotional state, academic performance, or ability to participate in your daily activities, many resources are available to help you through difficult times. Duke offers several resources for all students to seek assistance and to nurture daily habits that support overall well-being, some of which are listed below:
- DuWell, (919) 681-8421. DuWell provides Moments of Mindfulness (stress management and resilience building) and meditation programming (Koru workshop) to assist students in developing a daily emotional well-being practice. All are welcome and no experience necessary.
- DukeReach. DukeReach provides comprehensive outreach services to identify and support students in managing all aspects of well-being.
- Counseling and Psychological Services (CAPS), (919) 660-1000. CAPS services include individual and group counseling services, psychiatric services, and workshops. CAPS also provides referral to off-campus resources for specialized care. • TimelyCare (formerly known as Blue Devils Care). An online platform that is a convenient, confidential, and free way for Duke students to receive 24/7 mental health support through TalkNow and scheduled counseling.