COSC470: Special Topic - Machine Learning (2018)
Semester 2
Learning outcomes:
- An understanding of, an ability to use, and an ability to implement classical machine learning techniques (Information Literacy, Critical Thinking)
- An understanding of how AI agents play games and the most recent techniques for game playing (Information Literacy, Research, Critical Thinking, Lifelong Learning)
- An understanding of the basics of machine learning theory and how it applies to the recent success of deep learning (Information Literacy, Research, Critical Thinking)
- An ability to implement a deep learning model for a given task (Information Literacy, Critical Thinking, Research, Self-Motivation, Lifelong Learning)
- An understanding of the fundamentals of image recognition (Information Literacy, Critical Thinking, Research)
- An understanding of deep convolutional neural networks and an ability to use and implement such models (Information Literacy, Self-Motivation, Lifelong Learning)
- An ability to conduct AI experiments and successfully communicate the results (Information Literacy, Communication, Research, Lifelong Learning)
- An ability to find, read and understand recent research in the area (Information Literacy, Scholarship, Research, Lifelong Learning)
- An appreciation for the ethical problems associated with AI (Information Literacy, Ethics, Lifelong Learning)
Lecture outline:
- L1. Intro to classification and ML; decision trees
- L2. AdaBoost
- L3. SVMs
- L4. Basics of Learning Theory (and a bit of deep vs. shallow)
- L5. Deep Learning: classification/convnets/regularisation techniques etc.
- L6. Faces (Viola Jones detection and Eigenface recognition)
- L7. Convnets and image-based object recognition +
- L8. History of game playing, basic ideas, themes.
- L9. Deep reinforcement learning
- L10. The alphago breakthrough (and alphazero)
- L11. What next? [Are two player perfect information games just a solved case now? What are the more serious application cases?]
- L12. Issues with Face Recognition
- L13. Wrap-up, discussion of AI ethics.
Lecturers:
- Brendan McCane: L1-L3
- Michael Albert: L8, L10, L11
- Lech Szymanski: L4, L5, L9
- Steven Mills: L6, L7, L12
- Ali Knott and others: L13
Time:
Tuesday 9-11am