ago109/predictive-forward-forward

Implementation/simulation of the predictive forward-forward credit assignment algorithm for training neurobiologically-plausible recurrent neural network models.

33
/ 100
Emerging

This project offers an implementation of the Predictive Forward-Forward (PFF) algorithm, a method for training neural networks inspired by how brains learn. It takes in raw data, like images, and trains a dual-circuit neural system to predict and generate patterns. Researchers in computational neuroscience or artificial intelligence can use this to explore bio-plausible learning mechanisms.

No commits in the last 6 months.

Use this if you are a machine learning researcher or computational neuroscientist interested in simulating or extending novel, bio-plausible online learning algorithms for recurrent neural networks.

Not ideal if you are looking for a plug-and-play solution for standard deep learning tasks or if you don't have a background in neural network architectures and learning algorithms.

computational-neuroscience bio-plausible-learning recurrent-neural-networks predictive-coding machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

65

Forks

5

Language

Python

License

MIT

Last pushed

Apr 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ago109/predictive-forward-forward"

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