Why take this Machine Learning MOOC?

• Machine learning (ML) will soon be arriving in your organization, and you want to be ready.

• You’ve been using it for a while and want to keep up to date.

• You’re considering a career change and want to test your interest.

• You’re considering leading your company towards the adoption of artificial intelligence (AI).

• You’ve been asked to set up an AI group or project and would like to learn enough about the subject to manage it and recruit qualified staff.

• You simply have an interest in ML and AI and want to learn more.

You’ll be introduced to all the steps involved in an AA project. Want to predict the pressure inside a turbine based on data from multiple sensors? That’s regression! Want to predict whether or not a patient has diabetes based on the results of a medical examination? That’s classification! Want to group customers into different segments? That’s data clustering! There are many applications in a multitude of fields.

To properly apply ML to a project, you first need to understand the importance of the data, how to cleanse it in order to bring out its full value, and then which method in AA would extract the right information.

The course is divided into seven modules that you can follow at your own pace. You will be able to test your understanding with feedback through a quiz in each module.

This MOOC is the result of a collaboration between the Institut de valorisation des données (IVADO) at Université de Montréal, the Institut intelligence et données (IID) at Université Laval in Quebec City, and Mila – Institut québécois d’intelligence artificielle.

The content has been developed by professors, data scientists, computer scientists and engineers with experience in academic and industrial R&D.

Syllabus

Here are the theoretical and practical aspects of ML covered in each module:

• Module 1 – Introduction to ML

• Module 2 – Basic concepts

• Module 3 – Classical supervised methods : Preamble

  • Colab practice tutorial: Comparison of different regression methods

• Module 4 – Classical supervised methods

  • Colab practice tutorial: Comparison of different classification methods

• Module 5 – Advanced classical methods

  • Colab practice tutorial: Examples of deep learning

• Module 6 – Unsupervised learning methods

  • Colab practice tutorial 1: Example of data clustering in exploratory analysis

  • Colab tutorial 2: Example of data clustering in image analysis

• Module 7 – Industry application

  • Tutorial Colab 1: Examples of data preparation

  • Tutorial Colab 2: Selecting and optimizing an optimal model