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.
