Author:
Klyushin D. A., ,Maistrenko O. S.,
Abstract
The paper proposes a non-parametrical approach to explainable artificial intelligence based on the compactness postulate, which states that objects of one class in the feature space are, as a rule, located closer to each other than to objects of other classes. Objects are considered similar if they are located close to each other in the feature space. Meanwhile, the properties of objects in real life are often random values. Such objects are not described by a vector of features, but by a random sample or several samples of features, and the postulate of compactness should be replaced by the postulate of statistical homogeneity. Objects are considered statistically homogeneous if their features obey the same distributions. The paper describes a non-parametric measure of homogeneity and an illustration of its use in medical applications, in particular for the diagnosis of breast cancer within the framework of similarity-based explainable artificial intelligence.For comparison, the results of diagnostics of the same data set using deep learning of an artificial neural network are given. We formulate new statistical postulates of machine learning and propose to consider a machine learning algorithm as explanatory and interpretable if it satisfies these postulates.
Publisher
Taras Shevchenko National University of Kyiv
Reference45 articles.
1. Adadi A., Berrada M. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE Access 2018. Vol. 6. P. 52138-52160.
2. Alabdulhadi M., Coolen-Maturi T., Coolen F. Nonparametric predictive inference for comparison of two diagnostic tests. Communications in Statistics - Theory and Methods. 2021. Vol. 50. P. 4470-4486.
3. Amann J. et al. To explain or not to explain? - Artificial intelligence explainability in clinical decision support systems. PLOS Digital Health. 2022. Vol. 1(2). P. e0000016.
4. Andreichuk A. V., Boroday N. V., Golubeva K. M., Klyushin D. A. Artificial Intelligence System for Breast Cancer Screening Based on Malignancy-Associated
5. Changes in Buccal Epithelium. In: Enabling AI Applications in Data Science. Part of the Studies in Computational Intelligence book series (SCI, 2022, volume 911) Springer, 2022, pp. 267-285.