On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review

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 th...

Full description

Saved in:
Bibliographic Details
Published in:Computational Intelligence and Neuroscience 2015-01, Vol.2015 (2015), p.1252-1264
Main Authors: Laudani, Antonino, Lozito, Gabriele Maria, Riganti Fulginei, Francesco, Salvini, Alessandro
Format: Article
Language:English
Subjects:
Activation
Algorithms
Artificial Intelligence - economics
Back propagation
Computational efficiency
Efficiency
Feedback
Field programmable gate arrays
Humans
Mapping
Mathematical analysis
Mathematical models
Mathematical research
Networks
Neural networks
Neural Networks (Computer)
Neurons
Nonlinear theories
Review
Strategy
Studies
Teaching
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1687-5265
1687-5273
DOI:10.1155/2015/818243