. 2018 Dec 5;11(12):2467. doi: 10.3390/ma11122467

Table 1.

Structure and characteristics of the investigated neural networks. CV—convolutional layers (the brackets indicate the number of feature maps and the size of the kernels), MP—max-pooling layers (the brackets show the size of the pooling window), FC—fully connected layers (the brackets indicate the number of neurons).

No	CNN Model Description	w_k, px	Average Test Accuracy, %	Diagnostic Time, s
1.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–CV(32 × 3 × 3)–FC(1024)	15	92.81	45
2.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–FC(250)–FC(250)–FC(250)	10	92.41	19
3.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–FC(100)–FC(100)–FC(100)–FC(100)–FC(100)–FC(100)	10	92.39	17
4.	CV(32 × 5 × 5)–MP(2 × 2)–CV(64 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–FC(1024)	15	92.23	61
5.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–FC(400)–FC(400)	10	92.11	12
6.	CV(32 × 3 × 3)–MP(2 × 2)–FC(60)–FC(60)–FC(60)–FC(60)–FC(60)–FC(60)–FC(60)	10	92.08	8
7.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–FC(1024)	10	92.00	17
8.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–CV(32 × 3 × 3)–CV(32 × 3 × 3)–FC(1024)	10	91.91	24
9.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–FC(1024)	10	91.91	19
10.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–CV(32 ×3 × 3)–FC(200)–FC(200)	10	91.70	19
11.	CV(32 × 3 × 3)–MP(2 × 2)–FC(100)–FC(100)–FC(100)	10	91.50	9
12.	CV(48 × 3 × 3)–MP(2 × 2)–FC(50)–FC(50)–FC(50)–FC(50)–FC(50)–FC(50)–FC(50)–FC(50)–FC(50)	10	91,44	11
13.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–FC(1024)	10	91.22	19
14.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–CV(20 × 3 × 3)–FC(400)–FC(400)	7	90.70	11
15.	CV(32 × 3 × 3)–MP(2 × 2)–CV(32 × 3 × 3)–CV(32 × 3 × 3)–CV(32 × 3 × 3)–FC(1024)	7	90.60	13
16.	CV(20 × 3 × 3)–MP(2 × 2)–CV(30 × 3 × 3)–MP(2 × 2)–FC(200)–FC(200)	7	89.95	7
17.	CV(20 × 5 × 5)–MP(4 × 4)–CV(32 × 3 × 3)–MP(4 × 4)–FC(1024)	15	85.21	18