COMP5900: Advanced Machine Learning

Description

Machine learning (ML) is the scientific study of algorithms and statistical models that computers use in order to perform a specific task effectively without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. This course will cover advanced topics in machine learning such as deep learning, transfer learning, multiview learning, clustering and Interpretability of ML methods. Source

Content

Professor: Majid Komeili

Grade: in progress

Projects

The course is primarily project-based, with two assignments as well as a major research project. The assignments focused on:

  1. Convolutional Neural Networks
  2. Triplet loss

For the research project, I chose to explore large-scale relevance matching using tens of thousands of Tweets and associated news articles. You can check out my work here.

Presentations

The course also included presentations of two conference papers about a variety of topics. I chose to focus on interpretability in deep learning, and presented Attention is not Explanation as part of a small survey on the interpretability of the attention mechanism.

You can see my slides here (PDF).