Enhancing Interpretability in Machine Learning: A Focus on Genetic Network Programming, Its Variants, and Applications

被引：13

作者：

Roshanzamir, Mohamad ^{[1
]}

Alizadehsani, Roohallah ^{[2
]}

Moravvej, Seyed Vahid ^{[3
]}

Joloudari, Javad Hassannataj ^{[4
]}

Alinejad-Rokny, Hamid ^{[5
]}

Gorriz, Juan M. ^{[6
]}

机构：

[1] Fasa Univ, Fac Engn, Dept Comp Engn, Fasa, Iran

[2] Deakin Univ, Intelligent Syst Res & Innovat IISRI, Geelong, Vic, Australia

[3] Isfahan Univ Technol, Dept Elect & Comp Engn, Esfahan, Iran

[4] Tech & Vocat Univ TVU, Dept Comp Engn, Tehran, Iran

[5] UNSW Sydney, Grad Sch Biomed Engn, BioMed Machine Learning Lab, Sydney, NSW 2052, Australia

[6] Univ Granada, Dept Signal Theory Networking & Commun, Granada, Spain

来源：

ARTIFICIAL INTELLIGENCE FOR NEUROSCIENCE AND EMOTIONAL SYSTEMS, PT I, IWINAC 2024 | 2024年 / 14674卷

关键词：

Genetic Programming; Genetic Network Programming; Evolutionary Computing;

D O I：

10.1007/978-3-031-61140-7_10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In current machine learning research, deep learning methodologies have become the prevalent approach across various domains, including decision-making processes. However, the interpretability of solutions generated by these algorithms remains a significant challenge, as these models do not inherently prioritize explainability. This lack of interpretability hampers the analysis of decision-making rationales. One potential remedy to this issue is the employment of Genetic Network Programming (GNP), a method within the evolutionary computing paradigm, known for its ability to generate more interpretable solutions. This study provides a concise overview of GNP, exploring its modifications and applications to demonstrate its utility in addressing the interpretability challenge in machine learning algorithms.

引用

页码：98 / 107

页数：10

共 19 条

[1]

Chen Y., 2009, Machine Learning

[2] Investigating Genetic Network Programming for Multiple Nest Foraging [J].

Foss, Fredrik ;

Stenrud, Truls ;

Haddow, Pauline C. .

2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021), 2021,

[3]

Gonzales E, 2007, GECCO 2007: GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, VOL 1 AND 2, P1512

[4] Computational approaches to Explainable Artificial Intelligence: Advances in theory, applications and trends [J].

Gorriz, J. M. ;

Avarez-Illan, I. ;

Avarez-Marquina, A. ;

Arco, J. E. ;

Atzmueller, M. ;

Ballarini, F. ;

Barakova, E. ;

Bologna, G. ;

Bonomini, P. ;

Castellanos-Dominguez, G. ;

Castillo-Barnes, D. ;

Cho, S. B. ;

Contreras, R. ;

Cuadra, J. M. ;

Dominguez, E. ;

Dominguez-Mateos, F. ;

Duro, R. J. ;

Elizondo, D. ;

Fernandez-Caballero, A. ;

Fernandez-Jover, E. ;

Formoso, M. A. ;

Gallego-Molina, N. J. ;

Gamazo, J. ;

Gonzalez, J. Garcia ;

Garcia-Rodriguez, J. ;

Garre, C. ;

Garrigos, J. ;

Gomez-Rodellar, A. ;

Gomez-Vilda, P. ;

Grana, M. ;

Guerrero-Rodriguez, B. ;

Hendrikse, S. C. F. ;

Jimenez-Mesa, C. ;

Jodra-Chuan, M. ;

Julian, V. ;

Kotz, G. ;

Kutt, K. ;

Leming, M. ;

de Lope, J. ;

Macas, B. ;

Marrero-Aguiar, V. ;

Martinez, J. J. ;

Martinez-Murcia, F. J. ;

Martinez-Tomas, R. ;

Mekyska, J. ;

Nalepa, G. J. ;

Novais, P. ;

Orellana, D. ;

Ortiz, A. ;

Palacios-Alonso, D. .

INFORMATION FUSION, 2023, 100

[5]

Hirasawa K, 2001, IEEE C EVOL COMPUTAT, P1276, DOI 10.1109/CEC.2001.934337

[6]

Katagiri H., 2001, P 3 ANN C GEN EV COM, P179

[7]

Li X., 2010, IEEE C EV COMP, P1

[8] Niching genetic network programming with rule accumulation for decision making: An evolutionary rule-based approach [J].

Li, Xianneng ;

Yang, Meihua ;

Wu, Shizhe .

EXPERT SYSTEMS WITH APPLICATIONS, 2018, 114 :374-387

[9]

Li XN, 2014, 2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P1808, DOI 10.1109/CEC.2014.6900290

[10] A Learning Classifier System Based on Genetic Network Programming [J].

Li, Xianneng ;

Hirasawa, Kotaro .

2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013), 2013, :1323-1328

← 1 2 →