NN data

gistfile1.txt

Initial data vector 1: { 0.5, 0.5, 0.5, 0.5 } -> result 0
Initial data vector 2: { 0.3, 0.3, 0.5, 0.5 } -> result 1

Initial weights:
            double[] weights1 = { 0.1, 0.2, 0.3, 0.15,
                                  0.05, 0.21, 0.4, 0.1,
                                  0.43, 0.22, 0.20, 0.3 };
            double[] weights2 = { 0.1, 0.2, 0.3,
                                  0.08, 0.09, 0.3,
                                  0.04, 0.18, 0.1
                                };

            double[] weights3 = { 0.1, 0.2, 0.3 };


Weights after first training round:

weights 1 .092	.192	.292	.142	.031	.191	.381	.081	.405	.195	.175	.275	
weights 2 .07	.17	.268	.03	.04	.246	-.031	.109	.023	
weights 3 -.102	.003	.111	
NN (data vector 1) = 0.000138235472768235

Weights after second training round:

weights 1 .088	.188	.285	.135	.027	.187	.374	.074	.393	.183	.156	.256	
weights 2 -.009	.092	.186	.018	.028	.234	.027	.167	.084	
weights 3 .544	.618	.689	

NN (data vector 2) = 1.0013145773296

but then NN (data vector 1) = 1.00267206809212