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

Table 2

LHJ decomposition in Example 1.

	Template values	Logic operator	Margin
1	𝑤=(−1,−1,−1,−1,0,−1,−1,−1,1),−𝑏=−1		0.3536
2	𝑤=(−1,−1,−1,−1,−1,−1,−1,−1,−1),𝑏=−4	XOR	0.3333