2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS) 2016
DOI: 10.1109/isms.2016.14
|View full text |Cite
|
Sign up to set email alerts
|

An Analysis of the Regularization Between L2 and Dropout in Single Hidden Layer Neural Network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
37
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 81 publications
(37 citation statements)
references
References 11 publications
0
37
0
Order By: Relevance
“…Then, the detailed architecture of each component is elaborated. We, respectively, add the dropout layer [52] in DTB, UTB and bottleneck. Overfitting is a possibility as in deep convolutional neural network.…”
Section: Proposed Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Then, the detailed architecture of each component is elaborated. We, respectively, add the dropout layer [52] in DTB, UTB and bottleneck. Overfitting is a possibility as in deep convolutional neural network.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…Overfitting is a possibility as in deep convolutional neural network. The dropout layer [52] is used to prevent the overfitting problem and improve the segmentation accuracy. In addition to the DB, the bottleneck also can reduce the parameter size in DenseUNet without segmentation performance decline.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…Neurons are forced to learn, thus enhancing the network's generalization capability. L2 regularization improves generalization in linear models by penalizing weights in proportion to the sum of squares of weights [32]. We observed no signs of overfitting in the training graphs for the networks.…”
Section: Discussionmentioning
confidence: 67%
“…The number of neurons in each hidden layer of MLPs is heuristically set according to the problem to be processed. The more neurons there are, the stronger approximation ability of the network, and the greater risk of overfitting [ 20 ]. However, the number of neurons in the output layer is determined by the dimensions of the problem being processed.…”
Section: Principles Of the Basic Methodsmentioning
confidence: 99%