Table 7.

Optimum hyper-parameters results achieved by grid search of proposed CNN model 3 for classification of benign/malignant skin lesions in seven classes.

Hyper parameters	Hyper parameter range	Optimized value
Convolution layers	[3–9]	7
Max pooling layers	[1–4]	3
Fully connected layers	[2–5]	5
Activation function	[ReLU, Softmax, Sigmoid, Leaky ReLU]	ReLU, Softmax
Batch size	[16, 64, 128]	64
Learning rate	[0.0001, 0.01, 0.001, 0.00001]	0.001
Number of epochs	[10, 20, 30, 40, 50]	30