estebanvz/backpropagation_pso

Article about pso as neural network optimizer instead backpropagation

20
/ 100
Experimental

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.

Neural Network Optimization Evolutionary Algorithms Machine Learning Research AI Model Training Swarm Intelligence
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

GPL-3.0

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.