Table 1 Configuration table for the proposed DL architectures.

From: Stages prediction of Alzheimer’s disease with shallow 2D and 3D CNNs from intelligently selected neuroimaging data

Parameter

Configuration

Learning Rate

Initial Value

0.001

Nature

Timely Decreasing (Adaptive)

Reduction Factor

0.1

Minimum Possible Value

0.00001

Reduction Monitoring

Validation Accuracy

Patient to Reduction

2 times

Stopping Criteria

Stopping Monitoring

Validation Accuracy

Patience to Stop

4 times

Initial Learning Rate

0.01

Weights

Trainable

Yes

Initial Weights

Random

Training

Optimizer

Adam

Loss

Categorical Cross Entropy

Maximum Possible Epochs

Infinite

Batch Size

64

Validation Split

15%

Performance Metric

Accuracy

Back to article page