CIS4930/5930 Machine Learning -- Syllabus

Meeting Time and Place

MWF 1:25--2:15 pm, 103 Love Building

Course Webpage

https://www.alankuhnle.com/teaching/fa19ml/index.html

Important announcements / updates will be posted to the course website, as well as announced in class.

Course Instructor and Contact

Alan Kuhnle, email: [firstname]@[firstname][lastname].com

Office Hours

MW 11:30am -- 12:30 pm, 2:30pm--3:30pm, F 2:30pm--3:30pm MCH (Carothers) 106A, or by appointment.

Description

This course provides a rigorous introduction to modern topics within machine learning, listed below. Proofs and theoretical guarantees are emphasized throughout the course.

  • PAC learning framework
  • Rademacher Complexity & VC Dimension
  • Model Selection
  • Support vector machines
  • Kernel methods
  • Online learning
  • Regression
  • Dimensionality reduction
  • Reinforcement learning
  • Deep Feedforward Networks
  • Optimization for Training Deep Models

Prerequisites

Familiarity with sets and logic, analysis of algorithms, basic linear algebra, statistics, and calculus.

Textbooks

  1. Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar. Foundations of Machine Learning, 2nd edition (2018).
  2. Ian Goodfellow, Yoshua Benjio and Aaron Courville. Deep Learning.

Format

Reading will be assigned for each class session. Regular (usually biweekly) homework will be assigned, which will consist of written exercises and programming assignments. There will be two in-class exams.

To successfully complete this course you must read assigned texts, listen to lectures, and participate in discussions. Completing the assigned readings before their corresponding lectures and discussions will enable you to raise relevant questions and to improve your learning experience and your grade.

Homework

Homework will be collected at the beginning of class. Each assignment will be assigned a numerical score, and there will be a 10% penalty for late assignments turned in within 24 hours of the due date and a 50% penalty for assignments turned in more than 24 hours but less then 72 hours after the due date. Assignments submitted later than 72 hours will receive a grade of zero. Excuses for late assignments are made at the discretion of the instructor. The lowest assignment score for each student will be dropped.

You may use any sources, including classmates and online resources, as long as all sources are acknowledged on the assignment. To maximize your benefit from this class, you should attempt to solve the problems independently before consulting external resources.

Programming Assignments

Programming Assignments must be submitted to the TA by the due date. The format of each submission must be a tarball containing all source code, documentation for how to reproduce your results, and a report / summary of results. Programming assignments must be completed originally and individually; submissions that plagiarize code from any source will result in all parties receiving zero points for the assignment. Each assignment will be assigned a numerical score, and there will be a 10% penalty for late assignments turned in within 24 hours of the due date and a 50% penalty for assignments turned in more than 24 hours but less then 72 hours after the due date. Assignments submitted later than 72 hours will receive a grade of zero. Excuses for late assignments are made at the discretion of the instructor.

Exams

Exams will be given during class. Students who miss exams and/or makeup exams without a legitimate reason will receive a zero (0) for that exam. Questions, comments, concerns, and other issues about exams, homework, programming assignments, and other course-related matters should be brought to the attention of the instructor in a reasonable amount of time. A student will be allowed to make up a missed exam if the absence falls under the University Attendance Policy outlined below. Any other excuses will be at the discretion of the instructor and must be approved in advance.

Assessment

Numerical scores will be awarded based upon performance on homework assignments and exams. Each student will earn a score for each category: homework and exams. The categories will then be weighted as follows to compute the final grade:

  • Homework: 35%
  • Programming Assignments: 30%
  • Exams: 35%
Final numerical scores will be converted to letter grades for the course according to the following grading scale, which is subject to change:
  • 85% -- 100%: A
  • 70% -- 85%: B
  • 55% -- 70%: C
  • 40% -- 55%: D
  • 0% -- 40%: F
Plus / minus letter grades will be assigned near the boundaries of these cutoffs.

University Attendance Policy

Excused absences include documented illness, deaths in the family and other documented crises, call to active military duty or jury duty, religious holy days, and official University activities. These absences will be accommodated in a way that does not arbitrarily penalize students who have a valid excuse. Consideration will also be given to students whose dependent children experience serious illness.

Academic Honor Policy

The Florida State University Academic Honor Policy outlines the University's expectations for the integrity of students' academic work, the procedures for resolving alleged violations of those expectations, and the rights and responsibilities of students and faculty members throughout the process. Students are responsible for reading the Academic Honor Policy and for living up to their pledge to "...be honest and truthful and...[to] strive for personal and institutional integrity at Florida State University." (Florida State University Academic Honor Policy, found at http://fda.fsu.edu/Academics/Academic-Honor-Policy).

Americans with Disabilities Act

Students with disabilities needing academic accommodation should:

  1. register with and provide documentation to the Student Disability Resource Center; and
  2. bring a letter to the instructor indicating the need for accommodation and what type.
Please note that instructors are not allowed to provide classroom accommodation to a student until appropriate verification from the Student Disability Resource Center has been provided.

This syllabus and other class materials are available in alternative format upon request.

For more information about services available to FSU students with disabilities, contact the

Student Disability Resource Center
874 Traditions Way
108 Student Services Building
Florida State University
Tallahassee, FL 32306-4167
(850) 644-9566 (voice)
(850) 644-8504 (TDD)
sdrc@admin.fsu.edu
http://www.disabilitycenter.fsu.edu/
Syllabus Change Policy

This syllabus is a guide for the course and is subject to change with advanced notice. Changes to this syllabus must be accomplished in writing and posted to the appropriate sites.