The introduction of new topologies and training procedures to deep neural networks has solicited a renewed interest in the field of neural computation. The use of deep structures has significantly improved the state of the art in many applications, such as computer vision, speech and text processing, medical applications, and IoT (Internet of Things). The probability of a successful outcome from a neural network is linked to selection of an appropriate network architecture and training algorithm. Accordingly, much of the recent research on neural networks is devoted to the study and proposal of novel architectures, including solutions tailored to specific problems. The papers of this Special Issue make significant contributions to the above-mentioned fields by merging theoretical aspects and relevant applications. Twelve papers are collected in the issue, addressing many relevant aspects of the topic.

Innovative topologies and algorithms for neural networks

Graziani S.;Xibilia M. G.
2020-01-01

Abstract

The introduction of new topologies and training procedures to deep neural networks has solicited a renewed interest in the field of neural computation. The use of deep structures has significantly improved the state of the art in many applications, such as computer vision, speech and text processing, medical applications, and IoT (Internet of Things). The probability of a successful outcome from a neural network is linked to selection of an appropriate network architecture and training algorithm. Accordingly, much of the recent research on neural networks is devoted to the study and proposal of novel architectures, including solutions tailored to specific problems. The papers of this Special Issue make significant contributions to the above-mentioned fields by merging theoretical aspects and relevant applications. Twelve papers are collected in the issue, addressing many relevant aspects of the topic.
2020
Autoencoders
Convolution neural Networks
Gesture recognition
IoT (Internet of Thing) systems
Long-short-term memory networks
Medical applications
Object recognition
Sentiment analysis
Text recognition
File in questo prodotto:
File Dimensione Formato  
futureinternet-12-00117.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Dimensione 162.88 kB
Formato Adobe PDF
162.88 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/496234
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact