GEO-OPTIMIZER
Genetic & Evolutionary Optimizer for Neural Networks
A minimal, fully-customizable, mutation-based neural network optimizer inspired by evolutionary algorithms. No gradient descent. Just evolution.
What is GEO-OPTIMIZER?
GEO (Genetic and Evolutionary Optimizer) is a lightweight PyTorch-based framework for training neural networks using evolutionary strategies instead of traditional backpropagation.
- No gradients
- No backward()
- Works with any activation/loss functions
- Optimizes with mutation, selection, and survival of the fittest
How It Works
At each generation:
- A population of mutated neural networks is generated.
- Each network is evaluated using a loss function.
- The top 2 performers are selected.
- New weights are blended and passed to the next generation.
Installation
pip install geo-optimizer
1 maintainer
Metadata
1 maintainer
Release files for geo-optimizer 1.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| geo-optimizer-1.1.2.tar.gz | 6.6 kB | Without provenance | Details for geo-optimizer-1.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| geo_optimizer-1.1.2-py3-none-any.whl | Python 3 | none | any | Details for geo_optimizer-1.1.2-py3-none-any.whl |
Total release size: 12.9 kB
Release files / geo-optimizer-1.1.2.tar.gz
| Download URL | geo-optimizer-1.1.2.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
56daa911bbb99d90c2733954cecf76671554f4cfd19231eb9df0baf6b5f5239e
|
|
BLAKE2b-256 checksum How to use checksums |
e03ffbe4190fb5fdef3a998a01c82d4b2ec36a29cca329441fe27ab0730210fc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.0
|
Release files / geo_optimizer-1.1.2-py3-none-any.whl
| Download URL | geo_optimizer-1.1.2-py3-none-any.whl |
|---|---|
| Size | 6.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
103ae07480e233965115665b68e6b13022a9e5d45dc90b92cb73edcabb23b9e7
|
|
BLAKE2b-256 checksum How to use checksums |
20f9da8c2dcb68dc49060e987497737148c272df697d0489d6fd059078e2106e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.0
|
Security for geo-optimizer 1.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
