Korbinian Riedhammer

We will cover the basic concepts of prominent methods for generative deep learning before starting a deep dive on their application to text, audio and images. Since we will focus on applications and the usage of respective foundation models and toolkits, we strongly recommend you get familiar with deep learning ahead of this course. In detail, we will cover:

Theory: Prominent generative Deep Learning Methods
-Generative Pretrained Transformers (GPT), Fine-Tuning, RLHF, Instruction Learning, Zero-Shot Learning, In-Context Learning, Chain-of-Thought
-Generative Adversarial Networks (GAN)
-Variational Auto-Encoders (VAE)
-Diffusion
-Style transfer

Hands-On:
-Text: GPT Prompt Engineering
-Text to Speech, Voice Conversion
-Image generation and captioning


We will conclude the course with an outlook on risks, limitations, ethical and legal implications.

Over the last decade, Artificial Intelligence (AI) has seen a steep rise to the top, with large tech companies such as Google, Facebook, and Amazon investing heavily in research and development. From chatbots and face recognition algorithms to self‐driving cars, AI quickly transforms technology, business, and society. The driving factors behind this momentum are the recent advances in machine learning, particularly deep learning.
This course introduces the fundamental concepts of Deep Learning (DL). The objective is to provide a broad overview of the field, empowering you to understand the relationship between AI and DL and DL’s exciting and challenging application areas. Upon completing this course, you should be familiar with the common terminology in the field and understand its basic concepts. In addition, you will learn how distinct DL architectures can be applied to train your machine learning models. The detailed topics covered in the course include:
• Machine Learning Introduction
• Artificial Neural Networks (ANNs) and Backpropagation
• Convolutional Neural Networks (CNNs) and Autoencoders (AENs)
• Recurrent Neural Networks (RNNs) and Generative Adversarial Networks (GANs)
• Real-World Challenges and Trustworthy AI

We look forward to embarking on this exciting journey with you, exploring the cutting-edge concepts that are reshaping our technological landscape.