Table 5 Hyperparameters setting for base CNN model training.

From: Light convolutional neural network by neural architecture search and model pruning for bearing fault diagnosis and remaining useful life prediction

Name

Value

Batch size

36

Training epochs

20

\(\omega\) Learning rate

0.025

\(\omega\) Learning rate decay

0.001

\(\omega\) Learning rate momentum

0.9

Cells count

5

Random seed

2

\(\alpha\) Grad clip

5

\(\alpha\) Learning rate

3e−4

Back to article page