In earlier papers we presented a technique (“
”) for improving the performance of the solutions generated by
rogramming (GP) applied to regression and approximation of symbolic functions. RelaxGP changes the definition of a
solution: in standard symbolic regression, a perfect solution provides exact values for each point in the training set. RelaxGP allows a perfect solution to belong to a certain interval around the desired values.
We applied RelaxGP to regression problems where the input data is noisy. This is indeed the case in several “real-world” problems, where the noise comes, for example, from the imperfection of sensors. We compare the performance of solutions generated by GP and by RelaxGP in the regression of 5 noisy sets. We show that RelaxGP with relaxation values of 10% to 100% of the gaussian noise found in the data can outperform standard GP, both in terms of generalization error reached and in resources required to reach a given test error.