logo SBA

ETD

Digital archive of theses discussed at the University of Pisa

 

Thesis etd-02282019-191815


Thesis type
Tesi di dottorato di ricerca
Author
PEDRELLI, LUCA
email address
lucapedrelli@gmail.com
URN
etd-02282019-191815
Thesis title
Deep Reservoir Computing: A Novel Class of Deep Recurrent Neural Networks
Academic discipline
INF/01
Course of study
INFORMATICA
Supervisors
tutor Prof. Micheli, Alessio
tutor Dott. Gallicchio, Claudio
Keywords
  • Architectural Design of Recurrent Neural Networks
  • Deep Echo State Networks
  • Deep Learning
  • Deep Recurrent Neural Networks
  • Health Informatics
  • Multivariate Time-series Prediction
  • Polyphonic Music Composition
  • Reservoir Computing
  • Speech Recognition
Graduation session start date
08/03/2019
Availability
Full
Summary
In this thesis we propose a novel class of deep Recurrent Neural Networks (RNNs) explicitly extending the Reservoir Computing framework to the Deep Learning paradigm. Thereby, we introduce the Deep Echo State Network (DeepESN) model characterized by a hierarchy of randomized recurrent layers.
The introduction of randomized deep RNNs has provided tools to analyze deep recurrent models separately from learning algorithms aspects. The analysis and the experimental assessments conducted on DeepESNs highlighted that layering in deep RNNs is intrinsically able to develop hierarchical, distributed temporal features.
We evaluated our approach on controlled scenarios and challenging real-world tasks.
Overall, DeepESN models allowed us to design extremely efficient deep RNNs that obtained performance competing with state-of-the-art approaches.
File