细胞神经网络理论

细胞神经网络理论

Fig 5

%Fig 5
x = -5 : 5
y = -(abs(x + 1) - abs(x - 1)) + x
plot(x, y)

xlabel('Vxij')
ylabel('f(Vxij)')

Fig 9

%Fig 9

v_xij = [-0.8 1.0 -1.0 0.6;
          1.0 1.0 1.0 -1.0;
         -1.0 0.9 -1.0 -0.8;
         -0.9 -1.0 -0.7 -0.8]
T = [0 1 0;
     1 2 1;
     0 1 0]
 v_yij = 0.5 *  (abs(v_xij + 1) - abs(v_xij - 1)) %计算输出
 vx22 = [v_xij(2, 2)]
 vy22 = [v_yij(2, 2)]
 dt = 0.01
 for i = 1 : 499
    v_yijpadding = padarray(v_yij, [1,1], 'replicate') %填充，按照边界填充一圈
    dv_xij = (conv2(v_yijpadding, T, 'valid') - v_xij) * dt %计算变化值
    v_xij = v_xij + dv_xij %更新
    v_yij = 0.5 *  (abs(v_xij + 1) - abs(v_xij - 1)) %计算输出
    vx22 = [vx22 v_xij(2,2)] %扩充输入
    vy22 = [vy22 v_yij(2,2)] %扩充输出
 end
 
 t = 0 : 0.01 : 4.99
 grid on
 plot(t,vx22), hold on
 plot(t,vy22), hold on
 xlim([0, 5])
 ylim([0, 4])