Obtaining Basic Algebra Formulas with Genetic Programming and Functional Rewriting
In this paper, we develop a set of genetic programming operators and an initialization population process based on concepts of functional programming rewriting for boosting inductive genetic programming. Such genetic operators are used within a hybrid adaptive evolutionary algorithm that evolves operator rates at the same time it evolves the solution. Solutions are represented using recursive functions where genome is encoded as an ordered list of trees and phenotype is written in a simple functional programming language that uses rewriting as operational semantic (computational model). The fitness is the number of examples successfully deduced over the cardinal of the set of examples. Parents are selected following a tournament selection mechanism and the next population is obtained following a steady-state strategy. The evolutionary process can use some previous functions (programs) induced as background knowledge. We compare the performance of our technique in a set of hard problems (for classical genetic programming). In particular, we take as test-bed the problem of obtaining equivalent algebraic expressions of some notable products (such as square of a binomial, and cube of a binomial), and the recursive formulas of sum of the first n and squares of the first n natural numbers.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Interpretable Policies for Reinforcement Learning by Genetic Programming
The search for interpretable reinforcement learning policies is of high academic and industrial interest. Especially for industrial systems, domain experts are more likely to deploy autonomously learned controllers if th…
regressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Evolutional Math: Cross-Validated Island-Model Genetic Programming for Interpretable Symbolic Regression on Small, Wide Datasets
Symbolic regression via genetic programming routinely fails on small, wide datasets - a regime common in clinical-trial monitoring, biostatistics, and engineering pilot studies - by converging on bloated, overfit express…
An evolutionary approach for discovering non-Gaussian stochastic dynamical systems based on nonlocal Kramers-Moyal formulas
Discovering explicit governing equations of stochastic dynamical systems with both (Gaussian) Brownian noise and (non-Gaussian) L\'evy noise from data is chanllenging due to possible intricate functional forms and the in…
regressionDifferentiable Genetic Programming
We introduce the use of high order automatic differentiation, implemented via the algebra of truncated Taylor polynomials, in genetic programming. Using the Cartesian Genetic Programming encoding we obtain a high-order T…
Symbolic RegressionHash-Based Tree Similarity and Simplification in Genetic Programming for Symbolic Regression
We introduce in this paper a runtime-efficient tree hashing algorithm for the identification of isomorphic subtrees, with two important applications in genetic programming for symbolic regression: fast, online calculatio…
DiversityregressionSymbolic Regression