*Proceeding Paper* **Artificial Neural Networks Multicriteria Training Based on Graphics Processors †**

**Vladimir A. Serov \*, Evgenia L. Dolgacheva, Elizaveta Y. Kosyuk, Daria L. Popova, Pavel P. Rogalev and Anastasia V. Tararina**

> Department of Applied Information Technologie, MIREA—Russian Technological University (RTU MIREA), Moscow 119454, Russia; evgeniadolgacheva@yandex.ru (E.L.D.); kosyuk.ey@mail.ru (E.Y.K.); pdl13@yandex.ru (D.L.P.); radugapp@mail.ru (P.P.R.); nharvard2013@gmail.com (A.V.T.)

**\*** Correspondence: ser\_off@inbox.ru

† Presented at the 15th International Conference "Intelligent Systems" (INTELS'22), Moscow, Russia, 14–16 December 2022.

**Abstract:** The report considers the task of training a multilayer perceptron, formulated as a problem of multiobjective optimization under uncertainty. To solve this problem, the principle of vector minimax was used. A parallel software implementation of a hierarchical evolutionary algorithm for solving a multicriteria optimization problem under uncertainty based on a GPU is presented.

**Keywords:** artificial neural network; multicriteria optimization under uncertainty; vector minimax; parallel computing; GPU
