1
I am working on a TCC project that used neural networks in MATLAB as a universal function estimator, having obtained very good results: more than 70% of the samples present a relative error of less than 10% in relation to the real value, and 60% of the total has an error of less than 5% in relation to the real value.
However, I know what values the results should assume, are some discrete values, all known. I would like to improve my work, using some method to approximate the values obtained by the network to the real values, is that possible? Is there an algorithm, or some statistical analysis I can use?
For example, if I create an array of all possible values (there are 171 possible values), and compare the values found by the network with the possible values, and approximate to the nearest one, I can solve this problem for those with low relative error, which is about 70% of the total. But, assuming I don’t know the relative error, is there any method that I can increase the efficiency of my work?