On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review
Joint Authors
Laudani, Antonino
Lozito, Gabriele Maria
Salvini, Alessandro
Riganti-Fulginei, Francesco
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-08-31
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
A comprehensive review on the problem of choosing a suitable activation function for the hidden layer of a feed forward neural network has been widely investigated.
Since the nonlinear component of a neural network is the main contributor to the network mapping capabilities, the different choices that may lead to enhanced performances, in terms of training, generalization, or computational costs, are analyzed, both in general-purpose and in embedded computing environments.
Finally, a strategy to convert a network configuration between different activation functions without altering the network mapping capabilities will be presented.
American Psychological Association (APA)
Laudani, Antonino& Lozito, Gabriele Maria& Riganti-Fulginei, Francesco& Salvini, Alessandro. 2015. On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review. Computational Intelligence and Neuroscience،Vol. 2015, no. 2015, pp.1-13.
https://search.emarefa.net/detail/BIM-1057760
Modern Language Association (MLA)
Laudani, Antonino…[et al.]. On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review. Computational Intelligence and Neuroscience No. 2015 (2015), pp.1-13.
https://search.emarefa.net/detail/BIM-1057760
American Medical Association (AMA)
Laudani, Antonino& Lozito, Gabriele Maria& Riganti-Fulginei, Francesco& Salvini, Alessandro. On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review. Computational Intelligence and Neuroscience. 2015. Vol. 2015, no. 2015, pp.1-13.
https://search.emarefa.net/detail/BIM-1057760
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1057760