Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/53366
Title: Implementació d'una xarxa neural configurable amb optimització genètica
Author: Mas Mateo, Jordi
Tutor: Isern, David  
Others: Ventura, Carles  
Abstract: In this work, a multilayer perceptron neural network will be implemented, hyperparameters of which will be tuned by a genetic algorithm, that will try to find a near-optimal configuration for a given dataset. This is a proof of concept that will merge two algorithms inspired by nature: neural networks that imitates biological neurons operation, and genetic algorithms that mimics the natural selection. Algorithms like that had been proposed and studied before, but does not exist any implementation of it for the R statistical software. Thus, the final product of this work is an R package that will be distributed under the GPL.
Keywords: neural network
hyperparameters
genetic algorithms
Document type: info:eu-repo/semantics/bachelorThesis
Issue Date: 1-Jun-2016
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
JordiMas_TFG_0616.zipProducte37,64 MBZIPView/Open
jordimasTFG0716memòria.pdfMemòria del TFG1,11 MBAdobe PDFThumbnail
View/Open