Table 4 Hyperparameter tuning experiment for segmentation task model.

From: A machine learning approach for vocal fold segmentation and disorder classification based on ensemble method

Parameter

Search space

Selected value

Decay

[0.01, 0.0001, 0.00002]

0.00002

Optimizer

[Adam, RMSprop, Nadam]

RMSprop

Learning rate

[1e−4, 1e−4, 2e−4, 2e−3]

2e−4

Dropout

[0.1, 0.2]

0.2

Batch size

[8, 16, 32, 64]

16

Stride

[\(1\times 1, 2\times 2\)]

\(1\times 1\)

Padding

[Same, valid]

Same

Back to article page