Source
Neurocomputing
DATE OF PUBLICATION
03/02/2021
Authors
Mikhail Burtsev Dilyara Baymurzina Eugene Golikov
Share

A review of neural architecture search

Abstract

Despite the impressive progress in neural network architecture design, improving the performance of the existing state-of-the-art models has become increasingly challenging. For this reason, the paradigm for neural architecture design is shifting from being expert-driven to almost fully automated. An emerging body of research related to such machine-aided design is called a Neural Architecture Search (NAS). This paper reviews the recent works on NAS and highlights several crucial concepts and problems of this field.

Join AIRI