MT-CGP: Mixed Type Cartesian Genetic Programming

被引：20

作者：

Harding, Simon ^{[1
]}

Graziano, Vincent ^{[1
]}

Leitner, Juergen ^{[1
]}

Schmidhuber, Juergen ^{[1
]}

机构：

[1] IDSIA SUPSI USI, CH-6928 Manno, Switzerland

来源：

PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE | 2012年

关键词：

Cartesian Genetic Programming; Classifiers; NEURAL NETWORKS;

D O I：

10.1145/2330163.2330268

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The majority of genetic programming implementations build expressions that only use a single data type. This is in contrast to human engineered programs that typically make use of multiple data types, as this provides the ability to express solutions in a more natural fashion. In this paper, we present a version of Cartesian Genetic Programming that handles multiple data types. We demonstrate that this allows evolution to quickly find competitive, compact, and human readable solutions on multiple classification tasks.

引用

页码：751 / 758

页数：8

共 30 条

[1] An evolutionary artificial neural networks approach for breast cancer diagnosis [J].