Novel Surrogate Measures Based on a Similarity Network for Neural Architecture Search

We propose two novel surrogate measures to predict the validation accuracy of the classification produced by a given neural architecture, thus eliminating the need to train it, in order to speed up neural architecture search (NAS). The surrogate measures are based on a solution similarity network, w...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Zeki Kus, Can Akkan, Ayla Gulcu
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2023-01-01
Serier:	IEEE Access
Fag:	Neural architecture search surrogate model similarity-based prediction evolutionary algorithm
Online adgang:	https://ieeexplore.ieee.org/document/10058912/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!