Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

iDeepLe flowchart.

More »

Fig 1 Expand

Table 1.

Parameters setting for the grid-search stage 1.

More »

Table 1 Expand

Fig 2.

The architecture of the optimized deep neural network model.

More »

Fig 2 Expand

Table 2.

Properties of the activation functions used in different layers of iDeepLe.

More »

Table 2 Expand

Table 3.

Parameters setting for the grid-search stage 2.

More »

Table 3 Expand

Table 4.

Optimized hyper-parameters for the optimization algorithms after the grid-search stage 2.

More »

Table 4 Expand

Fig 3.

Density plots of the predictor input variables.

More »

Fig 3 Expand

Fig 4.

Scatter matrix presentation of the predictor input variables with their probability histograms.

More »

Fig 4 Expand

Table 5.

Parameters setting for the grid-search stage 3.

More »

Table 5 Expand

Fig 5.

10-folds cross-validation R2 during number of epochs for different batch sizes employing different optimization algorithms.

More »

Fig 5 Expand

Fig 6.

Statistical metrics for different batch sizes employing different optimization algorithms.

More »

Fig 6 Expand

Fig 7.

Histograms of the ratio of the predicted and the measured Ln(SA) for different batch sizes.

Mean and coefficient of variation of this ratio are also reported for different batch sizes. CB 2008 model has also been demonstrated for comparison.

More »

Fig 7 Expand

Table 6.

External validation results of the deep models with different batch sizes and CB 2008 model.

More »

Table 6 Expand

Table 7.

Parameters setting for the Adam optimizer using the popular deep learning libraries.

More »

Table 7 Expand

Fig 8.

Radar plots of the regression metrics for the most common regression models compared to iDeepLe model.

More »

Fig 8 Expand