NeuroEvo: A Cloud-based Platform for Automated Design and Training of Neural Networks using Evolutionary and Particle Swarm Algorithms

TL;DR

NeuroEvo is a cloud platform enabling users to design and train neural networks using evolutionary and particle swarm algorithms, with GPU acceleration and multi-language export options.

Contribution

This paper introduces NeuroEvo, a novel web-based platform that simplifies neural network optimization with evolutionary algorithms and provides accessible tools for users.

Findings

GPU parallelization significantly speeds up training

Users can customize neural network design and hyperparameters

Best classifiers are downloadable in multiple programming languages

Abstract

Evolutionary algorithms (EAs) provide unique advantages for optimizing neural networks in complex search spaces. This paper introduces a new web platform, NeuroEvo (neuroevo.io), that allows users to interactively design and train neural network classifiers using evolutionary and particle swarm algorithms. The classification problem and training data are provided by the user and, upon completion of the training process, the best classifier is made available to download and implement in Python, Java, and JavaScript. NeuroEvo is a cloud-based application that leverages GPU parallelization to improve the speed with which the independent evolutionary steps, such as mutation, crossover, and fitness evaluation, are executed across the population. This paper outlines the training algorithms and opportunities for users to specify design decisions and hyperparameter settings. The algorithms described in this paper are also made available as a Python package, neuroevo (PyPI: https://pypi.org/project/neuroevo/).