Please use this identifier to cite or link to this item:
Title: Xarxes neuronals recurrents per a sèries temporals
Author: Casals Lladó, Núria
Director: Fortiana Gregori, Josep
Keywords: Xarxes neuronals (Informàtica)
Treballs de fi de grau
Algorismes computacionals
Anàlisi de sèries temporals
Aprenentatge automàtic
Energia elèctrica
Neural networks (Computer science)
Bachelor's thesis
Computer algorithms
Time-series analysis
Machine learning
Electric power
Issue Date: 27-Jun-2018
Abstract: [en] Recurrent neural networks (RNNs) have been widely used for processing sequential data and are capable of learning long-term dependencies. This project proceeds from its inception, studying the behaviour of the simplest Deep Learning structures, to learning issues associated with time series data analysis to finally achieve more complex architectures: Long Short-Term Memory and Gated Recurrent Units. A model with a Gated Recurrent Unit has been implemented to forecast time series data associated with electricity consumption.
Note: Treballs Finals de Grau de Matemàtiques, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2018, Director: Josep Fortiana Gregori,
Appears in Collections:Treballs Finals de Grau (TFG) - Matemàtiques
Programari - Treballs de l'alumnat

Files in This Item:
File Description SizeFormat 
codi_font.zipCodi font1.75 MBzipView/Open
memoria.pdfMemòria1.99 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons