rmwkwok/forward_forward_algorithm
Implementation of Geoffrey Hinton's forward forward algorithm in tensorflow
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.
Stars
35
Forks
6
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
jolars/sortedl1
Python package for Sorted L-One Penalized Estimation (SLOPE)
gugarosa/opytimizer
🐦 Opytimizer is a Python library consisting of meta-heuristic optimization algorithms.
SENATOROVAI/gradient-descent-sgd-solver-course
Stochastic Gradient Descent (SGD) is an optimization algorithm that updates model parameters...
hiroyuki-kasai/SGDLibrary
MATLAB/Octave library for stochastic optimization algorithms: Version 1.0.20
softmin/ReHLine-python
Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence