Machine learning of a convolutional neural network based on a regularizing Bayesian approach
S.V. Prokopchina, P.E. Ryabov, Eugene Yu. Shchetinin · Neurocomputers · 2024
Machine learning is an essential component of the development of intelligent systems for various purposes. This article proposes a variant of machine learning for intelligent systems based on a regularizing Bayesian approach. The modes of learning in information processing in conditions of significant information uncertainty are considered. To form data sets, data and knowledge integration technologies are used to improve the efficiency of the systems and the quality of the solutions obtained.