Automated Machine Learning

This lecture will give an introduction to automated machine learning/deep learning.
It will mainly cover the following topics:

  • Hyperparameter Optimization
  • Bayesian Optimization
  • Neural Architecture Search
  • AutoML in the Age of Foundation Models

Unsupervised Deep Learning

This course covers unsupervised deep learning approaches, from basic clustering to advanced generative models. This includes a wide variety of modalities, such as images, text and audio:

  • Develop a deep understanding of current methods of unsupervised learning, self-supervised learning, representation learning and generative models.
  • Understand, apply and evaluate current approaches.
  • Understanding the technical underpinnings of unsupervised learning methods.
  • Evaluate and discuss new learning problems and unsupervised and self-supervised methods.

Selected topics are:

  • Basics of deep learning (CNNs, RNNs, Transformers)
  • Clustering and Feature Engineering
  • Generative Models
    • VAEs
    • Flow Models
    • Autoregressive Models
    • GANs
    • Diffusion Models