Mean Squared Error. More...

#include <evaluator.h>

Public Member Functions
	mse_error_functor (const T &)

double	operator() (const dataframe::example &) const

Detailed Description

template<class T>
class vita::mse_error_functor< T >

Mean Squared Error.

This fumctpr will drive the evolution towards the minimum sum of squared errors ( $\frac{1}{n} \sum_{i=1}^n (target_i - actual_i)^2$ ).

There is also a penalty for illegal values (it's a function of the number of illegal values).

Note: Real data always have noise (sampling/measurement errors) and noise tends to follow a Gaussian distribution. It can be shown that when we have a bunch of data with errors drawn from such a distribution you are most likely to find the "correct" underlying model if you seek to minimize the sum of squared errors.

Remarks: When the dataset contains outliers, the mse_error_functor will heavily weight each of them (this is the result of squaring the outliers). mae_error_functor is less sensitive to the presence of outliers (a desirable property in many applications).

Definition at line 178 of file gp/src/evaluator.h.

The documentation for this class was generated from the following file:

Public Member Functions