flxsosa/DeepHyperNEAT

A public python implementation of the DeepHyperNEAT system for evolving neural networks. Developed by Felix Sosa and Kenneth Stanley. See paper here: https://eplex.cs.ucf.edu/papers/sosa_ugrad_report18.pdf

43
/ 100
Emerging

This is a specialized tool for researchers and advanced practitioners in artificial intelligence and machine learning who want to automatically design complex neural network architectures. It takes high-level task definitions and evolutionary parameters, and outputs optimized neural network structures capable of solving those tasks, along with visualizations. The primary user would be an AI/ML researcher or an evolutionary computation engineer.

No commits in the last 6 months.

Use this if you need to evolve both the architecture and the depth of deep neural networks for a given computational task, rather than manually designing them.

Not ideal if you are looking for a plug-and-play machine learning library or a tool for general data analysis, as it requires a deep understanding of neuroevolutionary algorithms.

neuroevolution deep-learning AI-research neural-architecture-search evolutionary-computation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

77

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/flxsosa/DeepHyperNEAT"

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