Revistes Catalanes amb Accés Obert (RACO)

Learning from imprecise examples with GA-P algorithms

Luciano Sánchez Ramos, Ines Couso Blanco


GA-P algorithms combine genetic programming
and genetic algorithms to solve symbolic regression problems.
In this work, we will learn a model
by means of an interval GA-P procedure
which can use precise or imprecise
examples. This method provides us with an
analytic expression that shows the dependence
between input and output variables, using
interval arithmetic. The method also provides us with
interval estimations of the parameters on which this
expression depends.

The algorithm that we propose has been tested in a practical
problem related to electrical engineering. We will obtain
an expression of the length of the low voltage electrical
line in some spanish villages as a function
of their area and their number of inhabitants.
The obtained model is compared to
statistical regression-based, neural network, fuzzy rule-based
and genetic programming-based models.

Text complet: HTML