In the last decade, Neural Networks (NNs) have come to the fore as one of the most powerful and versatile approaches to many machine learning tasks. Deep Learning (DL), the latest incarnation of NNs, is nowadays applied in every scenario that needs models able to predict or classify data. From computer vision to speech-to-text, DL techniques are able to achieve super-human performance in many cases. This chapter is devoted to give a (not comprehensive) introduction to the field, describing the main branches and model architectures, in order to try to give a roadmap of this area to the reader.
Neural Networks and Deep Learning Fundamentals
Riccardo Zese
Primo
;Elena BellodiSecondo
;Michele Fraccaroli;Fabrizio RiguzziPenultimo
;Evelina LammaUltimo
2022
Abstract
In the last decade, Neural Networks (NNs) have come to the fore as one of the most powerful and versatile approaches to many machine learning tasks. Deep Learning (DL), the latest incarnation of NNs, is nowadays applied in every scenario that needs models able to predict or classify data. From computer vision to speech-to-text, DL techniques are able to achieve super-human performance in many cases. This chapter is devoted to give a (not comprehensive) introduction to the field, describing the main branches and model architectures, in order to try to give a roadmap of this area to the reader.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
full_text.pdf
solo gestori archivio
Descrizione: Full text editoriale
Tipologia:
Full text (versione editoriale)
Licenza:
Copyright dell'editore
Dimensione
582.68 kB
Formato
Adobe PDF
|
582.68 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.