Multi-objective parametric synthesis of loss functions in neural networks with evolutionary algorithms : доклад, тезисы доклада

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023); Krasnoyarsk; Krasnoyarsk

Год издания: 2024

Идентификатор DOI: 10.1051/itmconf/20245904010

Аннотация: The loss function is a fundamental aspect of neural network training and by choosing a suitable one, better results can be achieved. In classification problems, the cross-entropy loss function is almost exclusively used. In this paper the loss function represented by Taylor's series which are optimized with multi-objective evolutionary algorithm. As results show the new loss function can be better than cross-entropy, however application of multi-objective algorithm does not bring an improvement in comparison with single-objective algorithm.

Ссылки на полный текст

Издание

Журнал: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023)

Номера страниц: 4010

Место издания: Krasnoyarsk

Персоны

Morozov Eduard (Reshetnev Siberian State University of Science and Technology)
Stanovov Vladimir (Siberian Federal University)

Вхождение в базы данных

РИНЦ (eLIBRARY.RU)

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.