{"categories":[{"label":"Software Development","url":"https://skillfed.io/packages/category/software-development/17"},{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/8"},{"label":"Utilities","url":"https://skillfed.io/packages/category/utilities/11"},{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/10"},{"label":"Bio-Informatics","url":"https://skillfed.io/packages/category/scientific-engineering-bio-informatics"}],"enrichment":{"capability":"PyGAD is a Python library for building and running genetic algorithms to optimize single-objective and multi-objective problems, with built-in support for training Keras and PyTorch models.","skillfed_tags":["evolutionary-computation","hyperparameter-optimization","neural-network-training"],"use_cases":["Optimize weights or hyperparameters for a machine learning model when gradient-based methods are impractical or you want to explore a non-convex search space.","Train neural network weights using Keras or PyTorch by wrapping the model in a fitness function that evaluates test accuracy.","Solve combinatorial or discrete optimization problems (e.g., scheduling, routing) where you define fitness as a penalty-based score.","Multi-objective optimization where you balance competing goals (e.g., model accuracy vs. inference speed) in a single fitness metric.","Educational exploration of genetic algorithms and evolutionary computation with built-in lifecycle callbacks to trace algorithm behavior."],"what_it_does":"PyGAD is a genetic algorithm library that lets you define a fitness function and run an evolutionary optimization loop to find good solutions to single- or multi-objective problems. It handles population initialization, parent selection, crossover, and mutation automatically, with callback hooks at each stage so you can monitor or intervene in the algorithm's execution. The core library depends only on numpy and cloudpickle, keeping the base install lightweight; optional extras add visualization (matplotlib) and deep learning integration (Keras/PyTorch).\n\nYou write a fitness function that scores candidate solutions, then instantiate a GA object with your parameters (population size, number of generations, crossover/mutation strategy) and call run(). The library is actively maintained, supports current Python versions, and is documented with examples covering both simple optimization problems and neural network training scenarios.","worth_installing":"Yes. PyGAD is actively maintained, has low install friction, no known vulnerabilities, and a clear use case for evolutionary optimization and neural network training. The BSD 3-Clause license is permissive. Install it if you need genetic algorithm optimization; skip it if you only do gradient-based machine learning. Verify the license treatment classification if your use case has strict licensing requirements."},"id":"pygad","links":{"html":"https://skillfed.io/packages/pygad","md":"https://skillfed.io/packages/pygad.md","pypi":"https://pypi.org/project/pygad/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-06-05","license_spdx":null,"license_treatment":"unclear","name":"pygad","python_support":"supports_current","summary":"PyGAD: A Python Library for Building the Genetic Algorithm and Training Machine Learning Algoithms (Keras & PyTorch)."},"popularity":{"monthly_downloads":90134,"position":13617,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"3.7.0"}