xinglab-ai/mda

Revealing Hidden Patterns in Deep Neural Network Feature Space Continuum via Manifold Learning (Nature Communications, 2023)

27
/ 100
Experimental

When you're working with deep learning models, understanding how the model 'sees' and processes information at different internal steps can be difficult. This project helps visualize those hidden patterns by taking the complex, high-dimensional data from inside a deep neural network and transforming it into a clear, lower-dimensional map. This allows researchers and practitioners in fields like medical imaging, genomics, and risk prediction to see how their models are learning and making decisions.

No commits in the last 6 months.

Use this if you need to interpret the internal workings of a deep neural network and understand how features evolve through different layers for tasks like image segmentation, super-resolution, or predictive modeling.

Not ideal if you are looking for a tool to build or train deep learning models, as this focuses specifically on analyzing pre-trained model features.

deep-learning-interpretation medical-image-analysis genomic-prediction survival-analysis feature-visualization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Dec 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xinglab-ai/mda"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.