信息与控制2024，Vol.53Issue(2)：129-153,25.DOI:10.13976/j.cnki.xk.2024.3406
进化深度学习的研究现状与进展
Research Status and Progress in Evolutionary Deep Learning
摘要
Abstract
In recent years,both industry and academia have made significant advances in deep learning(DL).However,configuring the hyperparameters of deep models typically requires significant computational overhead and expert knowledge.To overcome these aforementioned challenges,evo-lutionary computation(EC),as an efficient heuristic search,has demonstrated significant advan-tages in the automated configuration of DL models,i.e.,evolutionary DL(EDL).We describe EDL from the perspective of automated machine learning.Particularly,we first depict the concept of EDL from EC and DL perspectives and regard EDL as an optimization problem.Consequently,we systematically introduce data preparation,model generation,and model deployment from the DL lifecycle.In addition,we analyze and discuss the solution representation and search paradigms.Finally,we provide applications,open issues,and potential research directions related to EDL.This study reviews the advancements in EDL and offers insightful guidelines for its development.关键词
进化计算/进化深度学习/数据准备/模型生成/模型部署Key words
evolutionary computation/evolutionary deep learning/data preparation/model generation/model deployment分类
计算机与自动化引用本文复制引用
李楠,贺美蕊,马连博..进化深度学习的研究现状与进展[J].信息与控制,2024,53(2):129-153,25.基金项目
国家自然科学基金项目(62032013,92267206) （62032013,92267206）
