### Abstract

Geometric Semantic Genetic Programming (GSGP) is a recent variant of Genetic Programming, that is gaining popularity thanks to its ability to induce a unimodal error surface for any supervised learning problem. Nevertheless, so far GSGP has been applied to the real world basically only on regression problems. This paper represents an attempt to apply GSGP to real world classification problems. Taking inspiration from Per-ceptron neural networks, we represent class labels as numbers and we use an activation function to constraint the output of the solutions in a given range of possible values. In this way, the classification problem is turned into a regression one, and traditional GSGP can be used. In this work, we focus on binary classification; logistic constraining outputs in [0,1] is used as an activation function and the class labels are transformed into 0 and 1. The use of the logistic activation function helps to improve the generalization ability of the system. The presented results are encouraging: our regression-based classification system was able to obtain results that are better than, or comparable to, the ones of a set of competitor machine learning methods, on a rather rich set of real-life test problems.

Original language | English |
---|---|

Title of host publication | Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) |

Editors | Juan Julian Merelo, Jonathan Garibaldi, Alejandro Linares-Barranco, Kurosh Madani, Kevin Warwick, Kevin Warwick |

Publisher | SciTePress |

Pages | 40-48 |

Number of pages | 9 |

Volume | 1 |

ISBN (Electronic) | 9789897583841 |

Publication status | Published - 1 Jan 2019 |

Event | 11th International Joint Conference on Computational Intelligence, IJCCI 2019 - Vienna, Austria Duration: 17 Sep 2019 → 19 Sep 2019 |

### Publication series

Name | IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence |
---|

### Conference

Conference | 11th International Joint Conference on Computational Intelligence, IJCCI 2019 |
---|---|

Country | Austria |

City | Vienna |

Period | 17/09/19 → 19/09/19 |

### Fingerprint

### Keywords

- Classification
- Geometric semantic genetic programming
- Regression

### Cite this

*Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019)*(Vol. 1, pp. 40-48). (IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence). SciTePress.

}

*Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019).*vol. 1, IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence, SciTePress, pp. 40-48, 11th International Joint Conference on Computational Intelligence, IJCCI 2019, Vienna, Austria, 17/09/19.

**A regression-like classification system for geometric semantic genetic programming.** / Bakurov, Illya; Castelli, Mauro; Fontanella, Francesco; Vanneschi, Leonardo.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A regression-like classification system for geometric semantic genetic programming

AU - Bakurov, Illya

AU - Castelli, Mauro

AU - Fontanella, Francesco

AU - Vanneschi, Leonardo

N1 - Bakurov, I., Castelli, M., Fontanella, F., & Vanneschi, L. (2019). A regression-like classification system for geometric semantic genetic programming. In J. J. Merelo, J. Garibaldi, A. Linares-Barranco, K. Madani, K. Warwick, & K. Warwick (Eds.), Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) (Vol. 1, pp. 40-48). (IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence). SciTePress.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Geometric Semantic Genetic Programming (GSGP) is a recent variant of Genetic Programming, that is gaining popularity thanks to its ability to induce a unimodal error surface for any supervised learning problem. Nevertheless, so far GSGP has been applied to the real world basically only on regression problems. This paper represents an attempt to apply GSGP to real world classification problems. Taking inspiration from Per-ceptron neural networks, we represent class labels as numbers and we use an activation function to constraint the output of the solutions in a given range of possible values. In this way, the classification problem is turned into a regression one, and traditional GSGP can be used. In this work, we focus on binary classification; logistic constraining outputs in [0,1] is used as an activation function and the class labels are transformed into 0 and 1. The use of the logistic activation function helps to improve the generalization ability of the system. The presented results are encouraging: our regression-based classification system was able to obtain results that are better than, or comparable to, the ones of a set of competitor machine learning methods, on a rather rich set of real-life test problems.

AB - Geometric Semantic Genetic Programming (GSGP) is a recent variant of Genetic Programming, that is gaining popularity thanks to its ability to induce a unimodal error surface for any supervised learning problem. Nevertheless, so far GSGP has been applied to the real world basically only on regression problems. This paper represents an attempt to apply GSGP to real world classification problems. Taking inspiration from Per-ceptron neural networks, we represent class labels as numbers and we use an activation function to constraint the output of the solutions in a given range of possible values. In this way, the classification problem is turned into a regression one, and traditional GSGP can be used. In this work, we focus on binary classification; logistic constraining outputs in [0,1] is used as an activation function and the class labels are transformed into 0 and 1. The use of the logistic activation function helps to improve the generalization ability of the system. The presented results are encouraging: our regression-based classification system was able to obtain results that are better than, or comparable to, the ones of a set of competitor machine learning methods, on a rather rich set of real-life test problems.

KW - Classification

KW - Geometric semantic genetic programming

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=85074291742&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

T3 - IJCCI 2019 - Proceedings of the 11th International Joint Conference on Computational Intelligence

SP - 40

EP - 48

BT - Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019)

A2 - Merelo, Juan Julian

A2 - Garibaldi, Jonathan

A2 - Linares-Barranco, Alejandro

A2 - Madani, Kurosh

A2 - Warwick, Kevin

A2 - Warwick, Kevin

PB - SciTePress

ER -