Directed Reading: Applied Deep Learning

Course Number
CHL7001H S1
7000 (Reading Courses & Research Projects)
Course Instructor(s)
Jodie Zhu

Course Description

The course will introduce practical and theoretical methodologies for applying deep learning to practical applications, including public health sciences, based on techniques employed in realworld contexts. Students will acquire familiarity with the fundamental organizational and technical requirements that need to be considered when putting deep learning applications into practice. The course will cover tensorflow, data preparation, model selection, model evaluation, advanced model architectures, debugging, infrastructure, model deployment, and ML in practical applications. The course will also review machine learning fundamentals and relevant theory. Upon completion, students will be able to develop and deploy systems that leverage machine learning in public health projects.

Course Objectives

By the end of the course students will be able to:

  1. understand how to best apply and evaluate machine learning models for research and
    practical settings;
  2. build and deploy systems that leverage machine learning to achieve goals;
  3. set up and maintain an ML development infrastructure to improve efficiency and
    shorten project timelines.

Methods of Assessment

Project 100%

  • proposal – 15% of the project mark
  • presentation – 25% of the project mark
  • report – 60% of the project mark

For more detailed information, please visit the course web page.

General Requirements

This course requires programming experience in Python as well as some background in linear
algebra and probability theory. Some prior experience/course work with machine learning
and/or data mining would be an asset.