Table 9.

CIFAR10 network topologies for AGD training methodology.

Model	Configuration	BackRes
VGG5	Input–Conv1(3,64,3x3/1)–Conv2(64,64,3x3/1)–	Not applicable
	–Pool(2x2/2)–Conv3(3,64,3x3/1)–Conv4(64,64,3x3/1)–
	–Pool(2x2/2)–FC1(4096,512)–FC2(512,10)
VGG3x2-v2	Input–Conv1(3,64,3x3/1)–Conv2(64,64,3x3/1)–	$\text{[Conv3]}$ repeated 2 times
	–Pool(2x2/2)–Conv3(3,64,3x3/1)–Conv3(64,64,3x3/1)–
	–Pool(2x2/2)–FC1(4096,512)–FC2(512,10)
VGG7	Input–Conv1(3,64,3x3/1)–Conv2(64,64,3x3/1)–	Not applicable
	–Pool(2x2/2)–Conv3(3,64,3x3/1)–Conv4(64,64,3x3/1)–
	–Conv5(3,64,3x3/1)–Conv6(64,64,3x3/1)–
	–Pool(2x2/2)–FC1(4096,512)–FC2(512,10)
VGG3x4	Input–Conv1(3,64,3x3/1)–Conv2(64,64,3x3/1)–	$\text{[Conv3]}$ repeated 4 times
	–Pool(2x2/2)–$\text{Conv3}(\mathrm{3,64,3}\times \mathrm{3/1})$$\text{–Conv3}(\mathrm{64,64,3}\times \mathrm{3/1})$–
	–$\text{Conv3}(\mathrm{3,64,3}\times \mathrm{3/1})$$\text{–Conv3}(\mathrm{64,64,3}\times \mathrm{3/1})$–
	–Pool(2x2/2)–FC1(4096,512)–FC2(512,10)

Notations are same as that of Table 3. Layers with BackRes connections and repeated computations have been highlighted in red.