PPKE ITK PhD and MPhil Thesis Classes
PPKE ITK PhD and MPhil Thesis Classes
PPKE ITK PhD and MPhil Thesis Classes
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
1.1 Cellular Neural/Nonlinear Network 5<br />
where u kl , x ij , <strong>and</strong> y kl are the input, the state, <strong>and</strong> the output variables. A <strong>and</strong><br />
B matrices are the feedback <strong>and</strong> feed-forward templates, <strong>and</strong> z ij is the bias term.<br />
N r (i,j) is the set of neighboring cells of the (i,j) th cell. The output y ij equation<br />
of the cell is described by the following function (see Figure 1.2):<br />
y ij = f(x ij ) = |x ij + 1| − |x ij − 1|<br />
2<br />
⎧<br />
⎨<br />
=<br />
⎩<br />
1 x ij (t) > 1<br />
x ij (t) −1 ≤ x ij (t) ≤ 1<br />
−1 x ij (t) < −1<br />
(1.2)<br />
f(V xij<br />
)<br />
1<br />
-1<br />
1<br />
V xij<br />
-1<br />
Figure 1.2: The output sigmoid function<br />
The discretized form of the original state equation (1.1) is derived by using<br />
the forward Euler form. It is as follows:<br />
x ij (n + 1)<br />
(<br />
= (1 − h)x ij (n)+<br />
)<br />
∑<br />
∑<br />
+h<br />
A ij,kl y kl (n) + B ij,kl u kl + z ij<br />
C (kl)∈N r(i,j)<br />
C (kl)∈N r(i,j)<br />
(1.3)<br />
In order to simplify computation variables are eliminated as far as possible (e.g.:<br />
combining variables by extending the template matrices). First of all, the Chua-<br />
Yang model is changed to the Full Signal Range (FSR) [20] model. Here the state<br />
<strong>and</strong> the output of the CNN are equal. In cases when the state is about to go to<br />
saturation, the state variable is simply truncated. In this way the absolute value<br />
of the state variable cannot exceed +1. The discretized version of the CNN state