基于无梯度进化的神经架构搜索算法研究综述

Review of Research on Neural Architecture Search AlgorithmsBased on Non-Gradient Evolution

自动化深度学习是目前深度学习领域的研究热点,神经架构搜索算法是实现自动化深度学习的主要方法之一,该类算法可以通过对搜索空间、搜索策略或优化策略进行不同定义来自动设计神经网络结构。阐述进化算法和进化神经网络的发展历程,分类介绍以进化算法为搜索策略实现神经架构搜索的方法和过程,并比较基于进化算法的不同神经架构搜索算法的特点和现状,在此基础上,对神经架构搜索算法的搜索空间、搜索策略以及算法的未来发展方向进行探讨和展望。

Automated deep learning is one of the new research hotspots in the field of deep learning.Neural architecture search algorithms are frequently used for the implementation of automated deep learning,as they can automatically design neural network structure by defining different search space,search strategy or optimization strategy.This paper introduces the development history of evolutionary algorithms and evolutionary neural networks.Then it introduces different methods and processes of using evolutionary algorithms as the search strategy to implement neural architecture search,and compares the features and development status of these neural architecture search algorithms.On this basis,this paper discusses the search space,search strategy and future development direction of neural architecture search algorithms.