Applying Genetic Programming to Improve Interpretability in Machine Learning Models

被引:0
|
作者
Ferreira, Leonardo Augusto [1 ]
Guimaraes, Frederico Gadelha [1 ]
Silva, Rodrigo [2 ]
机构
[1] Univ Fed Minas Gerais, UFMG, Dept Elect Engn, Machine Intelligence & Data Sci MINDS Lab, BR-31270000 Belo Horizonte, MG, Brazil
[2] Univ Fed Ouro Preto, UFOP, Dept Comp Sci, BR-35400000 Ouro Preto, MG, Brazil
关键词
Interpretability; Machine Learning; Genetic Programming; Explainability;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Explainable Artificial Intelligence (or xAI) has become an important research topic in the fields of Machine Learning and Deep Learning. In this paper, we propose a Genetic Programming (GP) based approach, name Genetic Programming Explainer (GPX), to the problem of explaining decisions computed by AI systems. The method generates a noise set located in the neighborhood of the point of interest, whose prediction should be explained, and fits a local explanation model for the analyzed sample. The tree structure generated by GPX provides a comprehensible analytical, possibly non-linear, expression which reflects the local behavior of the complex model. We considered three machine learning techniques that can be recognized as complex black-box models: Random Forest, Deep Neural Network and Support Vector Machine in twenty data sets for regression and classifications problems. Our results indicate that the GPX is able to produce more accurate understanding of complex models than the state of the art. The results validate the proposed approach as a novel way to deploy GP to improve interpretability.
引用
收藏
页数:8
相关论文
共 50 条
  • [21] INTERPRETABILITY OF MACHINE LEARNING MODELS: APPLICATION FOR LAWSUITS PREDICTION IN THE ENERGY SECTOR
    Cavalcante, Andre Borges
    [J]. PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27TH EDITION, 2020, : 17 - 17
  • [22] Latent Variable Machine Learning Framework for Catalysis: General Models, Transfer Learning, and Interpretability
    Kayode, Gbolade O.
    Montemore, Matthew M.
    [J]. JACS AU, 2023, 4 (01): : 80 - 91
  • [23] A Genetic Programming Encoder for Increasing Autoencoder Interpretability
    Schofield, Finn
    Slyfield, Luis
    Lensen, Andrew
    [J]. GENETIC PROGRAMMING, EUROGP 2023, 2023, 13986 : 19 - 35
  • [24] Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning
    Krishnan M.
    [J]. Philosophy & Technology, 2020, 33 (3) : 487 - 502
  • [25] How to improve the success of bank telemarketing? Prediction and interpretability analysis based on machine learning
    Xie, Chi
    Zhang, Jia-Le
    Zhu, You
    Xiong, Beibei
    Wang, Gang-Jin
    [J]. COMPUTERS & INDUSTRIAL ENGINEERING, 2023, 175
  • [26] Use of physics to improve solar forecast: Part II, machine learning and model interpretability
    Liu, Weijia
    Liu, Yangang
    Zhang, Tao
    Han, Yongxiang
    Zhou, Xin
    Xie, Yu
    Yoo, Shinjae
    [J]. SOLAR ENERGY, 2022, 244 : 362 - 378
  • [27] Use of physics to improve solar forecast: Part II, machine learning and model interpretability
    Liu, Weijia
    Liu, Yangang
    Zhang, Tao
    Han, Yongxiang
    Zhou, Xin
    Xie, Yu
    Yoo, Shinjae
    [J]. Solar Energy, 2022, 244 : 362 - 378
  • [28] Assessing the Interpretability of Machine Learning Models in Early Detection of Alzheimer's Disease
    Haddada, Karim
    Ibn Khedher, Mohamed
    Jemai, Olfa
    Khedher, Sarra Iben
    El-Yaeoubi, Mounim A.
    [J]. 2024 16TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTION, HSI 2024, 2024,
  • [29] On the Interpretability of Machine Learning Models and Experimental Feature Selection in Case of Multicollinear Data
    Drobnic, Franc
    Kos, Andrej
    Pustisek, Matevz
    [J]. ELECTRONICS, 2020, 9 (05)
  • [30] Applying machine learning techniques to improve linux process scheduling
    Negi, Atul
    Kishore, Kumar P.
    [J]. TENCON 2005 - 2005 IEEE REGION 10 CONFERENCE, VOLS 1-5, 2006, : 393 - +