Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/124823
Title: | Xarxes neuronals recurrents per a sèries temporals |
Author: | Casals Lladó, Núria |
Director/Tutor: | 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 theses 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, |
URI: | http://hdl.handle.net/2445/124823 |
Appears in Collections: | Programari - Treballs de l'alumnat Treballs Finals de Grau (TFG) - Matemàtiques |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
codi_font.zip | Codi font | 1.75 MB | zip | View/Open |
memoria.pdf | Memòria | 1.99 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License