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

Table 8

LHJ decomposition in Example 4.

	Template values	Logic operator	Margin
1	𝑤=(3,1,−1,1,3,2,1,3,2),𝑏=2		0.1601
2	𝑤=(0,0,1,−1,0,1,1,1,0),𝑏=−4	NAND	0.4472