thebuckleylab/jpc

Flexible Inference for Predictive Coding Networks in JAX.

45
/ 100
Emerging

This library helps neuroscientists and computational modelers build and train neural networks using Predictive Coding (PC) principles. You provide a neural network model, and it outputs the trained network capable of various tasks like classification or generation. This is designed for researchers who work with advanced neural network architectures and brain-inspired computing.

Use this if you are a computational neuroscientist or machine learning researcher interested in implementing and experimenting with Predictive Coding Networks (PCNs) for your models.

Not ideal if you are looking for a plug-and-play machine learning library for general-purpose tasks without specific interest in biologically plausible learning algorithms or JAX.

computational-neuroscience predictive-coding brain-inspired-ai neural-network-modeling cognitive-modeling
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

76

Forks

6

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thebuckleylab/jpc"

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