loeweX/Forward-Forward
Reimplementation of Geoffrey Hinton's Forward-Forward Algorithm
This project offers an alternative way to train deep neural networks that is inspired by how the brain learns. Instead of traditional methods, it processes 'real' data to enhance internal signals and 'fake' data to suppress them. This is useful for machine learning researchers and practitioners exploring novel deep learning architectures and training paradigms.
163 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner interested in experimenting with biologically inspired deep learning training methods as an alternative to backpropagation.
Not ideal if you are looking for a plug-and-play solution for standard deep learning tasks without wanting to delve into alternative training algorithms.
Stars
163
Forks
28
Language
Python
License
MIT
Category
Last pushed
Nov 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/loeweX/Forward-Forward"
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