Event box
Part 2 of 2: Generative AI with diffusion models
This three-part workshop will dive deeper into denoising diffusion models, which are a popular choice for text-to-image pipelines.
Applications of this technology include creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. Each session is roughly divided into 3 hours of interactive teaching and 1 hour of extra Q&A.
Three components below will spread over the two sessions:
- U-Net architecture and training a model to remove noise from an image.
- Autoencoders and variational autoencoders and then go toward diffusion models.
- Diffusion models and how to train them.
At the end of course, you can obtain a NVIDIA Certificate if you pass the assessment.
Important
This is a two-part course. Make sure you can attend both sessions before you register through session 1.
A laptop is required to participate. Students can borrow a laptop through the library’s Tech Lending program.
Prerequisites:
- A basic understanding of Deep Learning Concepts. (You may choose to register for the Fundamentals of Deep Learning workshop.)
- Familiarity with a Deep Learning framework such as TensorFlow, PyTorch, or Keras. This course uses PyTorch.
- Completion of session 1.
- Date:
- Monday, April 14, 2025
- Time:
- 1:00pm - 5:00pm
- Location:
- The Catalyst (Parks 199)
- Audience:
- Faculty Grad students & postdocs ISU staff Undergrads
- Categories:
- Workshop > The Catalyst
This workshop is part of a collaboration between Transitional AI Center (TrAC) and University Library to bring classes from the NVIDIA Deep Learning Institute to Iowa State. Questions about the program can be sent to trac@iastate.edu