Thanks to improvements in computing power and scientific theory, Generative AI is more accessible than ever before. Generative AI will play a significant role across industries and will gain significant importance due to its numerous applications such as Creative Content Generation, Data Augmentation, Simulation and Planning, Anomaly Detection, Drug Discovery, and Personalized Recommendations etc. In this course we will take a deeper dive on denoising diffusion models, which are a popular choice for text-to-image pipelines, disrupting several industries.
In order to participate in the advanced track, it is recommended that learners have some experience with:
- Good understanding of PyTorch
- Good understanding of deep learning
Workshop Sessions will run in two blocks: 8:30 am-12:30 pm and 1:30 pm-5:30 pm
By participating in this workshop, you’ll learn:
- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the Denoising Diffusion process
- Compare Denoising Diffusion Probabilistic Models (DDPMs) with Denoising Diffusion Implicit Models (DDIMs)
- Control the image output with context embeddings
- Generate images from English text-prompts using CLIP
Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Participants in this session will be asked to complete the following questions prior to the workshop:
- What is your current computer hardware?
- Do you use a multi-GPU cluster/workstation?
- What are the GPUs in the cluster/workstation?
- What is your current AI pipeline for medical images?
- Do you feel bottlenecked from compute power?
- Would multi-GPU work flow allow you to do bigger/better research in your current research focus?
- What DL framework do you use for your research?
- What value do you see in having state-of-the-art AI models ready to be used on your data with little to no coding changes?
Participants: The Advanced Track can host 40 total participants:
- 10 seats will be held for UF engineering students and allocated through a similar process as the seats for residents and fellows in the beginner track. These participants will receive $500 to cover their travel and free registration.
- 10 seats in-person: Open to all with a registration fee of $300
- 20 seats online: Open to all with a registration fee of $250.