{"title":"Neural networks: Studying their decision-making rules","authors":"Anatolii Petrenko, Ilya Vokhranov","doi":"10.20535/srit.2308-8893.2023.2.06","DOIUrl":"https://doi.org/10.20535/srit.2308-8893.2023.2.06","url":null,"abstract":"The question of a better understanding of the behavior of neural networks is quite relevant, especially in industries with a high level of risks. To solve this problem, the possibilities of the new DeepRED decomposition algorithm, capable of extracting decision-making rules by deep neural networks with several hidden layers, are explored in the paper. The study of the DeepRED algorithm was carried out on the example of extracting the rules of an experimental neural network during the classification of images of the MNIST database of handwritten digits, which made it possible to reveal a number of limitations of the DeepRED algorithm.","PeriodicalId":30502,"journal":{"name":"Sistemni Doslidzena ta Informacijni Tehnologii","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136300242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}