Trustworthy Machine Learning
Machine Learning (ML) is a subset of artificial intelligence (AI) that enables systems to learn and improve from experience without being explicitly programmed. It involves using data and algorithms to allow computers to identify patterns, make decisions, or predict outcomes. ML now replaces humans at many critical decision points and is used in various applications, such as healthcare, finance, e-commerce, software and technology, education, and law. However, as ML systems increasingly influence high-stakes domains, ensuring their safety, security, and overall trustworthiness gains a high importance. This also explains a recent global push for regulating ML models all over the world, including in Canada.
This seminar-style course will explore different topics in emerging research areas related to the development of trustworthy ML systems, i.e., systems that are reliable, secure, explainable, ethical, and also compliant with existing law and regulations. Students will learn about quality assurance methods for ML systems, attacks against ML systems, defense techniques to mitigate such attacks, and ethical implications of using ML systems.
The course assumes students already have a basic understanding of machine learning. Most of the course readings will come from both seminal and recent papers in the field. Each student will read, summarize, and present several scientific papers, as well as propose, implement, and present their own original project. As such, the course will also focus on polishing the students’ research, development, communication, and technical presentation skills.
3 credits
Learning Objectives
By the end of this course, students will learn:
- Foundations of Trustworthy Machine Learning;
- Quality assurance for ML systems;
- Robustness and reliability;
- Privacy in ML;
- Explainability and interpretability;
- Legal and ethical considerations;
- Efficient technical communication and presentation skills.
Course Prerequisites
This course does not have formal prerequisites. However, previous programming experience and a basic understanding of machine learning (equivalent to CPSC 340 or EECE 568) are necessary.