PyGAD: an intuitive genetic algorithm Python library

This paper introduces PyGAD, an open-source easy-to-use Python library for building the genetic algorithm (GA) and solving multi-objective optimization problems. PyGAD is designed as a general-purpose optimization library with the support of a wide range of parameters to give the user control over i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multimedia tools and applications Jg. 83; H. 20; S. 58029 - 58042
1. Verfasser: Gad, Ahmed Fawzy
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.06.2024
Springer Nature B.V
Schlagworte:
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Deep learning
Genes
Genetic algorithms
Libraries
Multimedia
Multimedia Information Systems
Multiple objective analysis
Mutation
Optimization
Python
Special Purpose and Application-Based Systems
Deep learning
PyTorch
Genetic algorithm
Evolutionary algorithm
Keras
Optimization
NumPy
Python
ISSN:1573-7721, 1380-7501, 1573-7721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper introduces PyGAD, an open-source easy-to-use Python library for building the genetic algorithm (GA) and solving multi-objective optimization problems. PyGAD is designed as a general-purpose optimization library with the support of a wide range of parameters to give the user control over its life cycle. This includes, but not limited to, the population, fitness function, gene value space, gene data type, parent selection, crossover, and mutation. Its usage consists of 3 main steps: build the fitness function, create an instance of the pygad.GA class, and call the pygad.GA.run() method. The library supports training deep learning models created either with PyGAD itself or with frameworks such as Keras and PyTorch. Given its stable state, PyGAD is also in active development to respond to the user’s requested features and enhancements received on GitHub.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-023-17167-y