Skip to main content

Table 4 Combinations of four algorithm hyperparameters for a pre-trained CNN model

From: Classifying microscopic images as acute lymphoblastic leukemia by Resnet ensemble model and Taguchi method

Number of experiments Algorithm hyperparameters
Optimizer MiniBatchSize MaxEpochs InitialLearnRate
1 adam 60 8 10−4
2 adam 65 10 10−5
3 adam 70 12 10−6
4 sgdm 60 10 10−6
5 sgdm 65 12 10−4
6 sgdm 70 8 10−5
7 adam 60 12 10−5
8 adam 65 8 10−6
9 adam 70 10 10−4