CAMELYON 17 Challenge: A Comparison of Traditional Machine Learning (SVM) with the Deep Learning Method

Table 5

Comparison of deep learning networks.

Network	Advantages	Disadvantages
GoogLeNet	Faster and more stable; high accuracy; the inception module is added, which can effectively lighten the phenomenon of gradient disappearance	A lot of computation
ResNet	It solves the degradation problem of network models and allows neural networks to be deeper	As the network deepens, the parameter complexity increases
VGG16	A deeper network model leads to better network performance and more accurate results	Maximum computation; Gradient disappearance
AlexNet	Minimum computation	Accuracy and stability are the worst