2016
DOI: 10.1007/978-3-319-28495-8
|View full text |Cite
|
Sign up to set email alerts
|

Artificial Neural Network Modelling

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0
1

Year Published

2018
2018
2023
2023

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 127 publications
(7 citation statements)
references
References 0 publications
0
6
0
1
Order By: Relevance
“…It worth noting that for the applications of MLPNN, the structures of neural networks (the number of the hidden layers, the amount of the neurons on each hidden layer) can be different. In fact, to define a proper network to obtain promising performance of data approximation is one of the main challenges of the applications of MLPNNs, and using growing neural networks as well as pruning technique are two of the ways to find proper networks for specific problems [36,46]. Besides, the uncertainty of MLPNNs in data approximation is another main challenge of the applications of MLPNNs, which includes input uncertainty, parameter uncertainty, and structure uncertainty [47].…”
Section: Multi-layer Perceptron Neural Network (Mlpnn)mentioning
confidence: 99%
See 2 more Smart Citations
“…It worth noting that for the applications of MLPNN, the structures of neural networks (the number of the hidden layers, the amount of the neurons on each hidden layer) can be different. In fact, to define a proper network to obtain promising performance of data approximation is one of the main challenges of the applications of MLPNNs, and using growing neural networks as well as pruning technique are two of the ways to find proper networks for specific problems [36,46]. Besides, the uncertainty of MLPNNs in data approximation is another main challenge of the applications of MLPNNs, which includes input uncertainty, parameter uncertainty, and structure uncertainty [47].…”
Section: Multi-layer Perceptron Neural Network (Mlpnn)mentioning
confidence: 99%
“…In fact, to define a proper network to obtain promising performance of data approximation is one of the main challenges of the applications of MLPNNs, and using growing neural networks as well as pruning technique are two of the ways to find proper networks for specific problems [36,46]. Besides, the uncertainty of MLPNNs in data approximation is another main challenge of the applications of MLPNNs, which includes input uncertainty, parameter uncertainty, and structure uncertainty [47]. A series of methods are proposed to quantify the uncertainties, therefore, to help users to evaluate the networks [47].…”
Section: Multi-layer Perceptron Neural Network (Mlpnn)mentioning
confidence: 99%
See 1 more Smart Citation
“…ANN adalah suatu model komputasi yang terinspirasi dari jaringan syaraf biologis. ANN terdiri dari elemen pemrosesan (neuron) dan koneksi antarneuron dengan koefisien (bobot) yang terikat pada koneksi tersebut (Shanmuganathan, 2016). Pada penelitian ini, beberapa arsitektur ANN yang akan diujikan ditetapkan dengan mempertimbangkan rules of thumb.…”
Section: Pendahuluanunclassified
“…The ANN is developed as a statistical optimization method that mimics the behavior of the biological nervous system [47,48]. They can generate logical models composed of several neurons that are interconnected in a computing environment.…”
Section: Extreme Learning Machine (Elm) Modelmentioning
confidence: 99%