Checkout my GitHub for coding projects
Towards Smaller Diffusion Models - Gaussian Mixture Masks and UNet Scaling
#Diffusion Models #Deep Learning #Research
Denoising diffusion probabilistic models (DDPMs) have demonstrated superior image generation capabilities but suffer from slow inference and high computational costs. As a first step to address these challenges, we propose two novel modifications to enhance small-scale diffusion models- Gaussian mixture masks and scaled skip connections. More details in the report or poster.
DeepMash
#Medical AI #Deep Learning #Research
Coded pipelines for DeepMash, a model forecasting patient’s likihood of death before receiving a transplant and deployed the model to the web. Check out the demo and the code repo.
Classify New Stars
#R #Research #EDA #Variable Selection #Machine Learning
Photography has always been one of my passions. For our project for STAT 441 Statistical Learning – Classification, we brought our passion for photography together with statistics and used NASA’s astrophotography data to classify new stellar observations.
Report (Code in Appendix), PowerPoint
