Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

Building Convolutional Neural Networks From Scratch using NumPy

Building and training artificial neural networks (regression or classification) using the genetic algorithm.

Implementation of Artificial Neural Networks using NumPy

Train PyTorch Models using the Genetic Algorithm with PyGAD

Training Keras Models by the Genetic Algorithm using PyGAD

Python Control System : Create control loops and let the AI set the PID parameters

This repo contains the code for neural network weight optimisation using 4 evolutionary algorithms.

Use genetic algorithm to train neuro network to play flappy bird game

A metaheuristic genetic algorithm route inspection problem solver for research purposes

A project in which nonogram puzzles are solved using genetic algorithms and swarm intelligence. The project compares the performance and quality of different solutions for different sizes of nonograms. The program was written in python using the pygad and pyswarms packages.

This genetic matching algorithm uses the PyGAD library to group users of StudyJio into groups of five.

Train a very small mnist model with genetic algorithm.

Snake GA - Genetic algorithm that solves the Snake game. GA was implemented by PyGAD library available for Python, neural networks was created in Keras and game was created in Pygame.

Federated Learning is simply the decentralized form of Machine Learning. Here we train a centralized Machine Learning model on decentralized data.

ImageContrastEnhancement is a demonstration of the capabilities of convolutional genetic algorithms in image processing, specifically in the area of contrast enhancement.

Automatically redraw any image into a painting by means of artificial evolution using the genetic algorithm with PyGAD.

Solving n queens puzzle with genetic algorithm.

Mathematical model, brute-force algorithm, and evolutionary algorithm for solving the internet shopping optimization problem