| IMMW Generative AI in Visual Computing | Course | INF | |
|---|---|---|---|
| Lecturers : | Term | 1 | |
| Course Classification : | Master Interactive Media (Winter-Immatrikulation), Wahlpflichtkatalog M-IM-W | CH | 4 |
| Language : | Deutsch/Englisch | Type | VÜS |
| Type of examination : | PL | Credits | 6 |
| Method of evaluation : | term paper with oral examination | ||
| Requirements : | |||
| Cross References : | |||
| Previous knowledges : | basic knowledge of computer graphics | ||
| Aids and special features : | |||
| Teaching aims : | In this course, students expand their knowledge at the intersection of Artificial Intelligence (AI) and Computer Graphics. They learn how Generative AI models are revolutionizing visual creativity and content creation. At the beginning, they gain practical knowledge in using AI tools and web UIs, with a focus on Stable Diffusion, Prompting, and the adaptation and extension of AI models through finetuning. As the course progresses, students deepen their understanding of deep learning techniques and develop skills in working with frameworks like TensorFlow and Keras. They learn to implement simple models and engage intensively with image generation. Fundamental technologies like Autoencoders, GANs, and Diffusion models are covered, which play a key role in the creation and editing of media content. The course combines technical expertise with creative design, allowing students to apply their acquired skills in hands-on, creative projects. By the end of the course, students will be able to use AI tools effectively to generate creative visual content, and will be able to evaluate and practically implement the potential and challenges of these technologies. | ||
| Contents : | * Introduction and Overview * Practical Insight into AI Tools for Image and Video Generation * Deep Learning Frameworks * Stable Diffusion Web UIs (User Interfaces) * Prompting for Generative AI * Customization and Extension of AI Models * Fundamentals of Neural Networks * Image Classification with Deep Learning Frameworks * Deep Computer Vision / Convolutional Neural Networks * Simple Generative Models – Autoencoders * Generative Adversarial Networks (GANs) * Diffusion Models, Text-to-Image Generators | ||
| Literature : | * Ian Goodfellow, Yoshua Bengio und Aaron Courville: Deep Learning, The MIT Press, 2016. * Simon J. D. Prince: Computer Vision: Models, Learning, and Inference, Cambridge University Press, 2012. * Rowel Atienza: Advanced Deep Learning with Tensorflow 2 and Keras, Packt Publishing, 2020. * Rajalingappaa Shanmugamani: Deep Learning for Computer Vision, Packt Publishing, 2018. * David Foster: Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play, O'Reilly Media, 2023 * current research papers | ||