A survey of randomized algorithms for training neural networks

As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Information sciences Ročník 364-365; s. 146 - 155
Hlavní autoři: Zhang, Le, Suganthan, P.N.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 10.10.2016
Témata:
Classification
Convergence
Convolutional neural networks
Deep learning
Networks
Neural networks
Randomization
Randomized neural networks
Recurrent neural networks
Regression
Statistics
Training
Deep learning
Recurrent neural networks
Randomized neural networks
Convolutional neural networks
ISSN:0020-0255, 1872-6291
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:As a powerful tool for data regression and classification, neural networks have received considerable attention from researchers in fields such as machine learning, statistics, computer vision and so on. There exists a large body of research work on network training, among which most of them tune the parameters iteratively. Such methods often suffer from local minima and slow convergence. It has been shown that randomization based training methods can significantly boost the performance or efficiency of neural networks. Among these methods, most approaches use randomization either to change the data distributions, and/or to fix a part of the parameters or network configurations. This article presents a comprehensive survey of the earliest work and recent advances as well as some suggestions for future research.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2016.01.039