IsmailKonak/FF-Algorithm-Pytorch-Implementation

The Forward-Forward Algorithm proposed by Geoffrey Hinton - Unofficial Pytorch Implementation

20
/ 100
Experimental

This is a specialized neural network training method that offers an alternative to the traditional backpropagation approach. It takes in positive and negative data examples, processing them in two forward passes to train each layer independently. This tool is for machine learning researchers and practitioners who are exploring new neural network architectures and learning algorithms.

No commits in the last 6 months.

Use this if you are a machine learning researcher or advanced practitioner experimenting with cutting-edge neural network training methodologies, particularly the Forward-Forward algorithm.

Not ideal if you are looking for a standard, production-ready deep learning solution or if you are unfamiliar with fundamental neural network concepts and research.

neural-network-research deep-learning-algorithms unsupervised-learning-methods machine-learning-experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IsmailKonak/FF-Algorithm-Pytorch-Implementation"

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