Search
Abstract
In this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings for different scenarios and variants of CNNs. Finally, the third part presents Neural Networks for sequence modeling, in particular Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) and Attention Mechanisms. The description of the latter models are made in the context of different applications that allows to explain in a better way the details of each particular kind of neural network.
Citations
-
3
CrossRef
-
0
Web of Science
-
5
Scopus
Authors (2)
-
A. Pastor López-Monroy
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Monographic publication
- Type:
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Title of issue:
- Biosignal Processing and Classification Using Computational Learning and Intelligence strony 177 - 196
- Language:
- English
- Publication year:
- 2022
- Bibliographic description:
- López-Monroy A. P., Garcia Salinas J.: Neural networks and deep learning// Biosignal Processing and Classification Using Computational Learning and Intelligence/ : , 2022, s.177-196
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/b978-0-12-820125-1.00021-x
- Verified by:
- Gdańsk University of Technology
seen 40 times