DoME: A deterministic technique for equation development and Symbolic Regression

This paper describes a new method for Symbolic Regression that allows to find mathematical expressions from dataset. has strong basis. As opposed other methods such as Genetic Programming, this is deterministic, and does not involve the creation of population initial solutions. Instead it, simple expression being grown until it fits data. The experiments performed show results are good Machine Learning methods, in very low computational time. Another advantage technique complexity can be limited, so system return easily analysed by user, opposition techniques like GSGP.