SciML/DeepEquilibriumNetworks.jl

Implicit Layer Machine Learning via Deep Equilibrium Networks, O(1) backpropagation with accelerated convergence.

45
/ 100
Emerging

This is a framework for machine learning practitioners and researchers to efficiently train and deploy Deep Equilibrium Networks (infinitely deep neural networks). It takes standard machine learning data as input and produces optimized, powerful neural network models that can solve complex problems with advanced computational methods. This is for users who want to leverage cutting-edge implicit layer techniques in their machine learning workflows.

Use this if you are a machine learning researcher or advanced practitioner looking to implement and train Deep Equilibrium Networks with accelerated performance and efficient backpropagation.

Not ideal if you are new to machine learning or prefer explicit, shallower neural network architectures for simpler tasks.

deep-learning neural-networks machine-learning-research scientific-computing
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

59

Forks

6

Language

Julia

License

MIT

Last pushed

Jan 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SciML/DeepEquilibriumNetworks.jl"

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