Table 15.

Network topologies for AGD training methodology with hybrid layers and stochmax classifier at the end.

Model	Configuration	BackRes
VGG9	Input–Conv1(3,64,3x3/1)-ReLU–	Not applicable
	–Conv2(64,64,3x3/1)-ReLU–Pool(2x2/2)–
	–Conv3(64,128,3x3/1)-LIF–
	–Conv4(128,128,3x3/1)-LIF–Pool(2x2/2)–
	–Conv5(128,256,3x3/1)-LIF–
	–Conv6(256, 256,3x3/1)-LIF–
	–Conv7(256,256,3x3/1)-LIF–Pool(2x2/2)–
	–FC1(4096,1024)-LIF–FC2(1024,10)
VGG8x2	Input–Conv1(3,64,3x3/1)-ReLU–	$\text{[Conv6]}$ repeated 2 times
	–Conv2(64,64,3x3/1)-ReLU–Pool(2x2/2)–
	–Conv3(64,128,3x3/1)-LIF–
	–Conv4(128,128,3x3/1)-LIF–Pool(2x2/2)–
	–Conv5(128,256,3x3/1)-LIF–
	–$\text{Conv6}(\mathrm{256,256,3}\times \mathrm{3/1})$-LIF–
	–$\text{Conv6}(\mathrm{256,256,3}\times \mathrm{3/1})$-LIF–Pool(2x2/2)–
	–FC1(4096,1024)-LIF–FC2(1024,10)

Notations are same as that of Table 3.