Metadata-Version: 2.1
Name: geo-optimizer
Version: 1.1.2
Summary: GEO: Genetic & Evolutionary Optimizer — A Neural Network Training framework.
Author: MrPsyghost (Shivay)
Author-email: shivaypuri2000@gmail.com
Project-URL: YouTube, https://www.youtube.com/@MrPsyghost
Keywords: neural networks,evolution,optimizer,genetic algorithm,deep learning,pytorch,neuroevolution,geo
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0.0
Requires-Dist: matplotlib>=3.10.0
Requires-Dist: rich>=13.0.0
Requires-Dist: tqdm>=4.0.0

# 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:
1. A **population** of mutated neural networks is generated.
2. Each network is evaluated using a **loss function**.
3. The **top 2 performers** are selected.
4. New weights are **blended and passed** to the next generation.

---

## Installation

```bash
pip install geo-optimizer
