Recent advances in deep learning

[...]DL models are deeper variants of artificial neural networks (ANNs) with multiple layers, whether linear or non-linear. [...]the convolution layers apply some filters to reduce complexity of the input data [12]. The pooling layers manage to reduce the size of the activation maps by transferring...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of machine learning and cybernetics Vol. 11; no. 4; pp. 747 - 750
Main Authors Wang, Xizhao, Zhao, Yanxia, Pourpanah, Farhad
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2020
Springer Nature B.V
Subjects
Algorithms
Artificial Intelligence
Artificial neural networks
Complex Systems
Complexity
Computational Intelligence
Control
Deep learning
Distance learning
Editorial
Engineering
Machine learning
Mechatronics
Neural networks
Pattern Recognition
Robotics
Systems Biology
Text categorization
Time series
Online AccessGet full text

Cover

More Information
Summary:[...]DL models are deeper variants of artificial neural networks (ANNs) with multiple layers, whether linear or non-linear. [...]the convolution layers apply some filters to reduce complexity of the input data [12]. The pooling layers manage to reduce the size of the activation maps by transferring them into a smaller matrix [13]. [...]pooling solves the over-fitting problem by reducing complexity [14]. [...]inspired by the rationality of DL-based methods and insightful characteristics underlying rain shapes, a specific coarse-to-fine de-raining network architecture is built.
Bibliography:SourceType-Scholarly Journals-1
content type line 14
ObjectType-Editorial-2
ObjectType-Commentary-1
ISSN:1868-8071
1868-808X
DOI:10.1007/s13042-020-01096-5