Skip to main content

A universal API for create artificial neural networks with a genetic code.

Project description

NeuroGenome is a bioinspired open-source project that allows you to create artificial neural networks with a genetic code.

Installation

pip install neurogenome

Settings example

# gene localization scheme
schema_0 = [
	[
		["i0","i1","i0","i1"],
		["h1","h0","h1","h0"]
	],
	[
		["i2","i3","i2","i3"],
		["h3","h2","h3","h2"]
	],
	[
		["o0","o1"],
		["o1","o0"]
	]
]

# hyperparameters
SETTINGS = {
	"population size": 50,
	"number of leaders": 5,
	"select by": "max",
	"number of input nodes per gene": 5,
	"number of hidden nodes per gene": 4,
	"number of output nodes per gene": 3,
	"schema": schema_0,
}

Examples

in the pipeline

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neurogenome-0.1.4.tar.gz (6.8 kB view hashes)

Uploaded Source

Built Distribution

neurogenome-0.1.4-py3-none-any.whl (8.3 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page