An Improved Algorithm for Eleman Neural Network by Adding a Modified Error Function

2007 ◽  
pp. 465-473
Author(s):  
Zhiqiang Zhang ◽  
Zheng Tang ◽  
GuoFeng Tang ◽  
Vairappan Catherine ◽  
XuGang Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Error Function ◽  
Improved Algorithm

scholarly journals An improved algorithm for neural network classification of imbalanced training sets

1993 ◽  
Vol 4 (6) ◽  
pp. 962-969 ◽  
Author(s):  
R. Anand ◽  
K.G. Mehrotra ◽  
C.K. Mohan ◽  
S. Ranka
Keyword(s):  
Neural Network ◽  
Neural Network Classification ◽  
Training Sets ◽  
Improved Algorithm

scholarly journals Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition

2018 ◽  
Vol 7 (3.15) ◽  
pp. 95 ◽  
Author(s):  
M Zabir ◽  
N Fazira ◽  
Zaidah Ibrahim ◽  
Nurbaity Sabri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Visual Recognition ◽  
Error Function ◽  
Network Models ◽  
Neural Network Models ◽  
California Institute Of Technology ◽  
Institute Of Technology ◽  
Similar Accuracy

This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models. 

Artificial Neural Network Learning of Nonstationary Behavior in Time Series

2003 ◽  
Vol 13 (02) ◽  
pp. 103-109 ◽  
Author(s):  
María I. Széliga ◽  
Pablo F. Verdes ◽  
Pablo M. Granitto ◽  
H. Alejandro Ceccatto
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Error Function ◽  
Input Parameter ◽  
Input Unit ◽  
Validation Data ◽  
Neural Network Learning ◽  
Secular Evolution ◽  
Artificial Neural

We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.

Sign in / Sign up

Export Citation Format

Share Document