An Efficient Method for Diagnosing Brain Tumors Based on MRI Images Using Deep Convolutional Neural Networks

Table 6

Comparison results between network architectures using ADAM and ADAS optimization algorithms.

CNN architectures	Training accuracy		Validation accuracy		Times (s)
	ADAM	ADAS	ADAM	ADAS	ADAM	DAS
DenseNet201	99.87%	99.88%	94.14%	95.39%	2455 s	2340 s
ResNet152V2	99.95%	99.97%	93.31%	94.47%	2927 s	3161 s
MobileNetV3	99.66%	99.71%	91.21%	95.39%	1398 s	1234 s
VGG19	99.91%	99.9%	92.88%	94.56%	2691 s	2447 s