estebanvz/backpropagation_pso
Article about pso as neural network optimizer instead backpropagation
This project explores using Particle Swarm Optimization (PSO) to train neural networks as an alternative to the standard backpropagation algorithm. It provides a practical demonstration for machine learning researchers and practitioners to compare different optimization approaches for their models. The input is a neural network model, and the output is a trained network using a non-traditional optimization method.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner interested in exploring alternative neural network optimization techniques beyond backpropagation.
Not ideal if you are looking for a plug-and-play solution for general-purpose neural network training, as it focuses on demonstrating a specific research concept.
Stars
8
Forks
—
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Feb 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/estebanvz/backpropagation_pso"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
icaros-usc/pyribs
A bare-bones Python library for quality diversity optimization.
SioKCronin/swarmopt
Swarm intelligence optimizer
ljvmiranda921/pyswarms
A research toolkit for particle swarm optimization in Python
Pattio/DeepSwarm
Neural Architecture Search Powered by Swarm Intelligence 🐜
kyegomez/swarms-pytorch
Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊