Fast-DENSER: Fast Deep Evolutionary Network Structured Representation
This paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). The approach is known as Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) and is capable of simultaneously optimising...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-06-01
|
Series: | SoftwareX |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S235271102100039X |
id |
doaj-722e338bb8ad4da2a27a148e65b258f6 |
---|---|
record_format |
Article |
spelling |
doaj-722e338bb8ad4da2a27a148e65b258f62021-05-26T04:27:42ZengElsevierSoftwareX2352-71102021-06-0114100694Fast-DENSER: Fast Deep Evolutionary Network Structured RepresentationFilipe Assunção0Nuno Lourenço1Bernardete Ribeiro2Penousal Machado3Corresponding author.; University of Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, PortugalUniversity of Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, PortugalUniversity of Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, PortugalUniversity of Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, PortugalThis paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). The approach is known as Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) and is capable of simultaneously optimising the topology, learning strategy and any other required hyper-parameters (e.g., data pre-processing or augmentation). Fast-DENSER has been successfully applied to numerous object recognition tasks, with the generation of Convolutional Neural Networks (CNNs). The code is developed and tested in Python3, and made available as a library. A simple and easy to follow example is described for the automatic search of CNNs for the Fashion-MNIST benchmark.http://www.sciencedirect.com/science/article/pii/S235271102100039XArtificial Neural NetworksAutomated machine learningNeuroEvolution |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Filipe Assunção Nuno Lourenço Bernardete Ribeiro Penousal Machado |
spellingShingle |
Filipe Assunção Nuno Lourenço Bernardete Ribeiro Penousal Machado Fast-DENSER: Fast Deep Evolutionary Network Structured Representation SoftwareX Artificial Neural Networks Automated machine learning NeuroEvolution |
author_facet |
Filipe Assunção Nuno Lourenço Bernardete Ribeiro Penousal Machado |
author_sort |
Filipe Assunção |
title |
Fast-DENSER: Fast Deep Evolutionary Network Structured Representation |
title_short |
Fast-DENSER: Fast Deep Evolutionary Network Structured Representation |
title_full |
Fast-DENSER: Fast Deep Evolutionary Network Structured Representation |
title_fullStr |
Fast-DENSER: Fast Deep Evolutionary Network Structured Representation |
title_full_unstemmed |
Fast-DENSER: Fast Deep Evolutionary Network Structured Representation |
title_sort |
fast-denser: fast deep evolutionary network structured representation |
publisher |
Elsevier |
series |
SoftwareX |
issn |
2352-7110 |
publishDate |
2021-06-01 |
description |
This paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). The approach is known as Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) and is capable of simultaneously optimising the topology, learning strategy and any other required hyper-parameters (e.g., data pre-processing or augmentation). Fast-DENSER has been successfully applied to numerous object recognition tasks, with the generation of Convolutional Neural Networks (CNNs). The code is developed and tested in Python3, and made available as a library. A simple and easy to follow example is described for the automatic search of CNNs for the Fashion-MNIST benchmark. |
topic |
Artificial Neural Networks Automated machine learning NeuroEvolution |
url |
http://www.sciencedirect.com/science/article/pii/S235271102100039X |
work_keys_str_mv |
AT filipeassuncao fastdenserfastdeepevolutionarynetworkstructuredrepresentation AT nunolourenco fastdenserfastdeepevolutionarynetworkstructuredrepresentation AT bernardeteribeiro fastdenserfastdeepevolutionarynetworkstructuredrepresentation AT penousalmachado fastdenserfastdeepevolutionarynetworkstructuredrepresentation |
_version_ |
1721426625749319680 |