ggbioing/mcvae
Multi-Channel Variational Auto Encoder: A Bayesian Deep Learning Framework for Modeling High-Dimensional Heterogeneous Data.
This project helps researchers and data scientists jointly analyze multiple types of data from the same subjects or experiments, such as different types of medical images, sensor readings, or survey responses. It takes in these diverse datasets and reveals underlying patterns, even when some data is missing. The output is a simplified, unified representation of your complex data, helping you uncover hidden relationships and generate new insights. It's ideal for anyone dealing with high-dimensional, multi-modal data in fields like healthcare or social science.
No commits in the last 6 months.
Use this if you need to understand the shared information across several distinct but related datasets, especially when some data points might be incomplete.
Not ideal if you are working with a single type of data or if your primary goal is simple predictive modeling without needing to interpret underlying latent factors.
Stars
31
Forks
5
Language
Python
License
—
Last pushed
Apr 24, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ggbioing/mcvae"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)