Практичні аспекти формування навчальних/тестових вибірок для згорткових нейронних мереж

The most common approaches to assessing the quality of training neural networks in the context of the problem of "small training sets" are analyzed. A review of the code implementation of the most universal approaches and ways of extending training/testing samples is carried out. The logic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Datum:2022
Hauptverfasser: Томка, Ю.Я., Талах, М.В., Дворжак, В.В., Ушенко, О.Г.
Format: Artikel
Sprache:English
Veröffentlicht: Vinnytsia National Technical University 2022
Schlagworte:
Online Zugang:https://oeipt.vntu.edu.ua/index.php/oeipt/article/view/611
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Назва журналу:Optoelectronic Information-Power Technologies

Institution

Optoelectronic Information-Power Technologies
Beschreibung
Zusammenfassung:The most common approaches to assessing the quality of training neural networks in the context of the problem of "small training sets" are analyzed. A review of the code implementation of the most universal approaches and ways of extending training/testing samples is carried out. The logic of the work of STN-module is analyzed. It can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimization process.