- author = "Leonardo Augusto Ferreira and Frederico Gadelha Guimaraes and Rodrigo Silva",
- title = "Applying Genetic Programming to Improve Interpretability in Machine Learning Models",
- booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC 2020",
- year = "2020",
- editor = "Yaochu Jin",
- pages = "paper id24516",
- address = "internet",
- month = "19-24 " # jul,
- organization = "IEEE Computational Intelligence Society",
- publisher = "IEEE Press",
- keywords = "genetic algorithms, genetic programming, XAI, Interpretability, Machine Learning, Explainability",
- isbn13 = "978-1-7281-6929-3",
-
DOI = "
doi:10.1109/CEC48606.2020.9185620",
- size = "8 pages",
- abstract = "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, named 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, symbolic 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.",
-
notes = "https://wcci2020.org/
Universidade Federal de Minas Gerais, Brazil; Universidade Federal de Ouro Preto, Brazil.
Also known as \cite{9185620}",
