Autors: Gospodinova, E. G., Mihailova, C. M.
Title: MATHEMATICAL MODELING FOR IMAGE RECOGNITION USING ARTIFICIAL INTELLIGENCE
Keywords: mathematical modeling, neural network, image, algorithm

Abstract: In this paper, we study a mathematical model for pattern recognition using neural networks. A feed-forward neural network was built with the capabilities of a graphics accelerator, based on the Levenberg-Marquardt method. The introduced model summarizes and proposes a new neural network training algorithm with Bayes regularization, Nguyen-Widrow initialization, and the early stopping and control method. This enables and greatly expands the efficiency of solving problems where pattern recognition is available.

References

    Issue

    Announcements of Union of Scientists, vol. 38, issue 2, pp. 33-38, 2023, Bulgaria, Union of scientists in Bulgaria-branch Sliven, ISBN ISSN - 1311-2864

    Вид: пленарен доклад в национален форум с межд. уч., публикация в реферирано издание