rmwkwok/forward_forward_algorithm

Implementation of Geoffrey Hinton's forward forward algorithm in tensorflow

30
/ 100
Emerging

This tool helps machine learning researchers explore and implement Geoffrey Hinton's Forward-Forward (FF) algorithm. It provides modular building blocks, like `FFLayer`s and a `TrainMgr`, to design and test different FF training sequences. Researchers working on novel neural network architectures or alternative training methods would use this to prototype and experiment.

No commits in the last 6 months.

Use this if you are a machine learning researcher interested in experimenting with the Forward-Forward algorithm's layers and custom training loops without the constraints of traditional model APIs.

Not ideal if you need a plug-and-play solution for standard deep learning tasks or are looking for a highly optimized, production-ready FF implementation.

neural-network-research deep-learning-algorithms unsupervised-learning alternative-training-methods machine-learning-experimentation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

35

Forks

6

Language

Jupyter Notebook

License

Last pushed

Feb 27, 2023

Commits (30d)

0

Get this data via API

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

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