Overview

An introduction to machine learning theories and algorithms. Topics include Supervised Learning (e.g. Regression, Deep Neural networks, and SVM) and Probabilistic Graphical Models (e.g. Bayesian networks and Markov models). Programming assignments and projects are required.

Course Outcomes

Students will be able to:

  • Describe the types of problems that machine learning techniques are used to solve, and which machine learning algorithms are appropriate for solving each type of problem.
  • Describe, compare, and contrast different machine learning algorithms.
  • Implement machine learning algorithms using labeled data.
  • Work as a team to implement solutions to complex, real world machine learning problems.
  • Describe evaluation techniques for assessing and comparing machine learning techniques.

Instructor

Cyril Weerasooriya

Email at tcw at cs.rit.edu

Digesting the Course

Due to COVID-19, there will be no in-person classes this summer and the medium of instruction would be virtual. I will release a media package to the Contents section every Sunday evening (by 11:59 EST) of the week of each given topic. They will resemble slides, but may contain videos, notes, articles, etc..

We will organize weekly discussions based on your responses to the onboarding survey Google Form.

Schedule

WeekStart DateTopic to be coveredProject MilestonesHomework
15/14/2020Introduction, data, real world issues, linear algebra, and statistics
25/21/2020Numerical methods, optimization, calculusHW 1 [Release]
35/28/2020Supervised Machine learning
46/4/2020Feedforward neural networks, Keras, TensorflowProject 1 dueHW 1 [Data] due
56/11/2020CNNsHW 2 [Release]
66/18/2020Regularization over neural networks and other practical topics
76/25/2020OptimizationHW 2 [Nets] due
87/2/2020Sequence learning: Markov models
97/9/2020HMMs, LSTMsProject 2 due
107/16/2020Dimensionality reductionHW 3 [Release]
117/23/2020Unsupervised Learning
127/30/2020Reinforcement learningHW 3 [RL] due
138/5/2020Wrap upFinal Exam [Aug 9]

Mental Health and Well-Being

Success in this course depends heavily on your personal health and wellbeing. Recognize that stress is an expected part of the college experience, and it often can be compounded by unexpected setbacks or life changes outside the classroom. Your other instructors and I strongly encourage you to reframe challenges as an unavoidable pathway to success. Reflect on your role in taking care of yourself throughout the term, before the demands of exams and projects reach their peak. Please feel free to reach out to me about any difficulty you may be having that may impact your performance in this course as soon as it occurs and before it becomes unmanageable. In addition to myself, your other instructors, and your academic advisor, I strongly encourage you to contact the many other support services on campus that stand ready to assist you.

For urgent mental health concerns during business hours: Monday-Friday 8:30 a.m.-4:30 p.m. Call 585-475-2261 

For urgent matters that cannot wait for business hours:  Call 1-855-436-1245 to speak with a mental health provider or call Public Safety at 585-475-3333