SGP-DT: Semantic Genetic Programming Based on Dynamic Targets
This work addresses the challenge of reducing approximation error and computational cost in evolutionary computation for researchers in the field, though it appears incremental.
The paper tackles the problem of improving semantic genetic programming by introducing a dynamic target approach that divides the search into multiple runs guided by residual errors, resulting in an average 23.19% smaller RMSE compared to a state-of-the-art method.
Semantic GP is a promising approach that introduces semantic awareness during genetic evolution. This paper presents a new Semantic GP approach based on Dynamic Target (SGP-DT) that divides the search problem into multiple GP runs. The evolution in each run is guided by a new (dynamic) target based on the residual errors. To obtain the final solution, SGP-DT combines the solutions of each run using linear scaling. SGP-DT presents a new methodology to produce the offspring that does not rely on the classic crossover. The synergy between such a methodology and linear scaling yields to final solutions with low approximation error and computational cost. We evaluate SGP-DT on eight well-known data sets and compare with ε-lexicase, a state-of-the-art evolutionary technique. SGP-DT achieves small RMSE values, on average 23.19% smaller than the one of ε-lexicase.