# Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution

Source: [Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution](<https://www.sota2.com/research/paper/68fa667d1e209131cea108bb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:51:21.649Z

Authors: Filip Badan, Lukas Sekanina

Published: 2019-10-15T15:15:39.000Z

## Abstract

Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the classification error and CNN complexity (expressed as the number of tunable CNN parameters), in which the inference phase can partly be executed using fixed point operations to further reduce power consumption. Experimental results are obtained with TinyDNN framework and presented using two common image classification benchmark problems -- MNIST and CIFAR-10.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.06854>)

[PDF](<https://arxiv.org/pdf/1910.06854.pdf>)