Robust Template Decomposition without Weight Restriction for Cellular Neural Networks Implementing Arbitrary Boolean Functions Using Support Vector Classifiers

Table 12

LHJ Decomposition in Example 6.

	Template values	Logic operator	Margin
1	𝑤=(2,−2,−1,1,3,−2,0,0,0),𝑏=1		0.2085
2	𝑤=(1,−1,1,2,1,−1,0,0,0),𝑏=−3	XOR	0.3780
3	𝑤=(−1,1,0,0,0,−1,0,0,0),𝑏=−2	OR	0.5774
4	𝑤=(−1,−2,1,2,1,−1,0,0,0),𝑏=3	AND	0.2887
5	𝑤=(1,1,0,1,0,1,0,0,0),𝑏=−3	OR	0.5000
6	𝑤=(−1,0,0,0,1,−1,0,0,0),𝑏=−2	OR	0.5774
7	𝑤=(1,1,0,0,1,0,0,0,0),𝑏=2	AND	0.5774
8	𝑤=(1,−1,1,−1,0,0,0,0,0),𝑏=−3	OR	0.5000