PCS956 Research Trends in Applied Machine Learning

Contents and structure

This course explores cutting-edge developments in applied machine learning (ML), examining how sophisticated algorithms and computational systems extract actionable insights from complex, high-dimensional data. Students will investigate the theoretical foundations and practical applications that drive innovation across diverse domains, from large language models revolutionizing natural language processing to advanced computer vision systems enabling autonomous perception.

The curriculum adapts to reflect the rapid evolution of the field, with particular emphasis on emerging research directions such as uncertainty quantification, causal inference, and time-series among others. Through a combination of research paper discussions, hands-on implementations, and project work, students will develop the analytical skills necessary to contribute to this rapidly advancing field.

Learning Outcome

Upon completion, students will demonstrate proficiency in:

Knowledge

• explain the mathematical frameworks underlying machine learning methods that covered in the course, as well as how these methods are applied in selected application domains.
• problems assessment to select and apply suitable ML methods and software tools to solve them.
• some practical skills include designing strategies and implementing ML solutions.

Skills

• design solution strategies for machine learning problems,
• implement machine learning based solutions for some of the application domains that covered in the course.

General competence:

• develop solutions for real-life problems,
• work in multidisciplinary environment,
• technical communication.

Entry requirements

In addition to meeting the general PhD program admission requirements, students should possess:

• Background in linear algebra and probability/statistics
• Familiarity with fundamental machine learning concepts
• Proficiency in Python programming, particularly with data science libraries

Note: Students with gaps in these prerequisite areas are welcome to enroll but they need to dedicate additional time to self-study. We recommend:

• Reviewing foundational machine learning concepts through online resources (e.g., Stanford's CS229 Machine Learning, MIT Introduction to Machine Learning, etc.)
• Strengthening Python programming skills.

The course assumes these foundational skills to focus on advanced topics and current research developments.

Recommended previous knowledge

Having elementary-level coursework on machine learning or statistical inference is highly recommended.

Teaching methods

Lectures, e-learning materials, discussions, and projects.

Compulsory learning activities

Student activity expected during lectures, seminars, and workshop activities.

Assessment

The course is graded pass/fail based on assignments (including project's report) and an oral exam. Each of the two components must result in a pass grade in order to obtain a pass grade for the entire course.

Examination support material

Assignment (e.g. project report and presentation): All support material is permitted

Oral exam: No support material

More about examination support material