Please use this identifier to cite or link to this item: http://hdl.handle.net/10316/100856
Title: Fast-DENSER: Fast Deep Evolutionary Network Structured Representation
Authors: Assunção, Filipe 
Lourenço, Nuno 
Ribeiro, Bernardete 
Machado, Penousal 
Keywords: Artificial Neural Networks; Automated machine learning; NeuroEvolution
Issue Date: 2021
Project: FCT project CISUC - UID/CEC/ 00326/2020 
FCT Grant No: SFRH/BD/114865/2016 
FEDER Regional Operational Program Centro 2020 
Serial title, monograph or event: SoftwareX
Volume: 14
Abstract: 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
URI: http://hdl.handle.net/10316/100856
ISSN: 23527110
DOI: 10.1016/j.softx.2021.100694
Rights: openAccess
Appears in Collections:I&D CISUC - Artigos em Revistas Internacionais

Files in This Item:
File Description SizeFormat
1-s2.0-S235271102100039X-main.pdf411.95 kBAdobe PDFView/Open
Show full item record

Google ScholarTM

Check

Altmetric

Altmetric


This item is licensed under a Creative Commons License Creative Commons