Oxford, United Kingdom

Advanced Artificial Intelligence and Machine Learning: Deep Unsupervised Learning

Deep Unsupervised Learning is an exciting emerging area of research in the field of artificial intelligence and machine learning, in which the goal is to develop systems that can learn from unlabelled data. Such systems closely mimic natural human intelligence by finding patterns in data without instructions on what to look for.

The course will begin with an introduction to unsupervised learning and clustering algorithms, before exploring generative adversarial networks and deep generative models. You will examine self-supervised learning, anomaly detection, flow-based models, and unsupervised representation learning. The final part of the course focuses on clustering in high-dimensional spaces, semi-supervised learning, energy-based models, and unsupervised learning for reinforcement.

This intensive course offers theoretical understanding and practical experience with a focus throughout on real-world applications of deep unsupervised learning across various domains, offering career skills as well as excellent foundations for future research.

Target group

This course would suit STEM students with intermediate level experience in artificial intelligence and machine learning concepts and techniques, including those undertaking, or looking ahead to, graduate level study or research.

Specifically, students on this course must have experience of the following topics:
- Knowledge of the deep learning libraries.
- Understanding of deep learning, recurrent neural networks, and convolutional neural networks.
- Strong background in optimization and probability.
- Familiarity with the Python programming language.

Course aim

By the end of this course, you will:
- Understand the differences between supervised and unsupervised learning and the fundamentals of clustering.
- Be able to utilise a range of algorithms and techniques for unsupervised, self-supervised, and semi-supervised learning.
- Be able to evaluate the efficacy of real-world applications of deep unsupervised learning across various domains.
- be able to demonstrate familiarity with the current state of research into deep unsupervised learning.

Credits info

7.5 EC
LMH Summer Programmes are designed to be eligible for credit, and we recommend the award of 7.5 ECTS / 4 US / 15 CATS for this course.

Fee info

GBP 1360: This includes:
- All tuition, including lectures, seminars, and tutorials.
- Assessment, transcript of academic performance, and certificate.
- Access to the LMH Summer Programmes remote learning platform.
- Support of the dedicated Remote Learning Coordinator.