logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-05232019-155650


Tipo di tesi
Tesi di laurea magistrale
Autore
NARDO, STEFANO
URN
etd-05232019-155650
Titolo
An Empirical Comparison of Recurrent Neural Networks on Sequence Modeling
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA
Relatori
relatore Prof. Micheli, Alessio
relatore Dott. Gallicchio, Claudio
Parole chiave
  • machine learning
  • neural networks
  • reti neurali
Data inizio appello
14/06/2019
Consultabilità
Non consultabile
Data di rilascio
14/06/2089
Riassunto
Recurrent Neural Networks (RNNs) are amongst the most powerful Machine Learning models to deal with sequential data. Many RNN architectures have been proposed over the years. We review three of the most used RNN architectures: the Standard Recurrent Network, the Long Short-Term Memory and the Gated Recurrent Unit. Furthermore, the Reservoir Computing (RC) has emerged as an alternative paradigm in the area of RNNs, whose the Echo State Network represents the most used model. In addition, minimum complexity RC-based networks have been developed, such as the Delay Line Reservoir and the Simple Cycle Reservoir.. We conduct several experiments on a varied set of problems, in order to compare their performances and analyze their correlation. Furthermore, we create a software framework to build RC models.
File