Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning

BMC Bioinformatics

Table 10 Googlenet model with different algorithm hyperparameters: accuracy for training and testing sets

Case number	Hyperparameters				Accuracy for training set	Accuracy for testing set
Case number	Optimizer	MiniBatchSize	MaxEpochs	InitialLearnRate	Accuracy for training set	Accuracy for testing set
1	sgdm	80	5	10^–4	0.9409	0.9680
2	sgdm	60	5	10^–4	0.9495	0.9835
3	sgdm	40	5	10^–4	0.9527	0.9845
4	sgdm	40	4	10^–4	0.9472	0.9607
5	sgdm	20	3	10^–4	0.9494	0.9452
6	sgdm	20	2	10^–4	0.9480	0.9804

ISSN: 1471-2105