A framework for exploring and modeling neural architecture search methods

Скорочена інформація про документ
dc.contributor.authorRadiuk, Pavlo
dc.contributor.authorHrypynska, Nadiia
dc.date.accessioned2021-12-14T11:34:06Z
dc.date.available2021-12-14T11:34:06Z
dc.date.issued2020-05-14
dc.descriptionhttp://ceur-ws.org/Vol-2604/paper70.pdfuk_UA
dc.description.abstractFor the past years, many researchers and engineers have been developing and optimising deep neural networks (DNN). The process of neural architecture design and tuning its hyperparameters remains monotonous, timeconsuming, and do not always ensure optimal results. In his regard, the automatic design of machine learning (AutoML) has been widely utilised, and neural architecture search (NAS) has been actively developing in recent years. Despite meaningful advances in the field of NAS, a unified, systematic approach to explore and compare search methods has not been established yet. In this paper, we aim to close this knowledge gap by summarising search decisions and strategies and propose a schematic framework. It applies quantitative and qualitative metrics for prototyping, comparing, and benchmarking the NAS methods. Moreover, our framework enables categorising critical areas to search for better neural architectures.uk_UA
dc.identifier.citationRadiuk P. M., Hrypynska N. V. A framework for exploring and modeling neural architecture search methods // CEUR-Workshop Proceedings. 2020. Vol. 2604. P. 1060-1074.uk_UA
dc.identifier.urihttps://elar.khmnu.edu.ua/handle/123456789/11048
dc.language.isoenuk_UA
dc.publisherCEUR-WSuk_UA
dc.subjectdeep neural networkuk_UA
dc.subjectAutoMLuk_UA
dc.subjectneural architecture searchuk_UA
dc.subjectscheme modellinguk_UA
dc.subjectefficient neural networkuk_UA
dc.titleA framework for exploring and modeling neural architecture search methodsuk_UA
dc.typeСтаттяuk_UA
Файли
Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
paper70.pdf
Розмір:
512.66 KB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Назва:
license.txt
Розмір:
4.26 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити
Зібрання
Кафедра комп’ютерних наук