Numeric Mutation: Improved Search in Genetic Programming
Matthew P. Evett, Thomas V. Fernandez · 1998
Genetic programming is relatively poor at discovering useful numeric constants for the terminal nodes of its s-expression trees. In this paper we outline an adaptation to genetic programming, called numeric mutation. ~,Ve provide empirical evidence and analysis that demon-strate that numeric mutation makes a statistically sig-nificant increase in genetic programming’s performance for symbolic regression problems.