Workshop: Generative AI with Diffusion Models

Date/Time:	Monday, 04 Nov 2024 from 1:00 pm to 3:00 pm
Location:	199 Parks Library, The Catalyst
Cost:	Free
URL:	www.lib.iastate.edu
Contact:	Transitional AI Center,
Phone:	515-294-1442
Channel:	University Library
Categories:	Training, development
Actions:	Download iCal/vCal | Email Reminder

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. Registration required.

---

Workshop details and registration are available on the University Library website.

This is a three-part course. Make sure you can attend all three sessions before you register.
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.
Familiarity with a Deep Learning framework such as TensorFlow, PyTorch, or Keras. This course uses PyTorch.

The first session (Nov. 4) will introduce U-Net architecture and training a model to remove noise from an image.
The second session (Nov. 11) will focus on autoencoders and variational autoencoders and then go toward diffusion models.
The third session (Nov. 18) focuses on diffusion models and how to train them.

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.