Please use this identifier to cite or link to this item:

Можете відсканувати цей QR-код телефоном( програмою "Сканер QR-кодів" ) для збереження.

Title: A Framework for Exploring and Modelling Neural Architecture Search Methods
Authors: Radiuk, Pavlo
Hrypynska, Nadiia
Keywords: deep neural network;AutoML;neural architecture search;scheme modelling;efficient neural network
Issue Date: 2020
Citation: Radiuk P. A Framework for Exploring and Modelling Neural Architecture Search Methods / P. Radiuk, N. Hrypynska // IV International Conference on Computational Linguistics and Intelligent Systems (CoLInS 2020) : Conference Program, April 23-24, 2020. - Lviv, Ukraine, 2020.
Abstract: For 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.
metadata.dc.type: Стаття
Appears in Collections:Кафедра телекомунікацій, медійних та інтелектуальних технологій

Files in This Item:
File Description SizeFormat 
paper70.pdf524,36 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.