There are two different Self Organizing Map (SOM) models in the figures given below. For the input vectors x1 = (0.1, -0.4)*, x2 = (-1,0.2), X3 = (0.8,0.8),..., X1000 = (0.6,0.9) which model is more suitable? Why? After x, and x, vectors have been applied to the SOM you have chosen, calculate the new code vectors (neurons). no = (0,1), n = (0.3, 0.3), n2 = (0.2,0.6), n3 = (-0.6,0.4), n4 = (-1,0), ns = (0,7,-0.1), ng = (-0.3, 0.9), n = (0.7,-0.1), ng = (1,-1) no n1 n2 no nl) n2 n5 n4 n3 n3 n5 n6 n7 n8 n6 ns (0,5 if li- c = 1 Bc, n) 0,1 if li- c = 2 1 if li- c = 0 lo other values 0 where c = BMU index, n; = Updated neuron with index i Learning rate a = 0.5k where k = train number There are two different Self Organizing Map (SOM) models in the figures given below. For the input vectors x1 = (0.1, -0.4)*, x2 = (-1,0.2), X3 = (0.8,0.8),..., X1000 = (0.6,0.9) which model is more suitable? Why? After x, and x, vectors have been applied to the SOM you have chosen, calculate the new code vectors (neurons). no = (0,1), n = (0.3, 0.3), n2 = (0.2,0.6), n3 = (-0.6,0.4), n4 = (-1,0), ns = (0,7,-0.1), ng = (-0.3, 0.9), n = (0.7,-0.1), ng = (1,-1) no n1 n2 no nl) n2 n5 n4 n3 n3 n5 n6 n7 n8 n6 ns (0,5 if li- c = 1 Bc, n) 0,1 if li- c = 2 1 if li- c = 0 lo other values 0 where c = BMU index, n; = Updated neuron with index i Learning rate a = 0.5k where k = train number