适配硬件和任务的One-shot神经网络架构搜索

批准号:
62006226
项目类别:
青年科学基金项目
资助金额:
24.0 万元
负责人:
陈亚冉
依托单位:
学科分类:
机器学习
结题年份:
2023
批准年份:
2020
项目状态:
已结题
项目参与者:
陈亚冉
国基评审专家1V1指导 中标率高出同行96.8%
结合最新热点,提供专业选题建议
深度指导申报书撰写,确保创新可行
指导项目中标800+,快速提高中标率
微信扫码咨询
中文摘要
神经网络架构搜索(Neural Architecture Search, NAS)通过设计高效的搜索方法,自动获取性能优异的网络结构,避免算法开发过程中大量的人工调优工作,降低算法开发难度,因而NAS的研究备受关注。然而,面向实际应用,适配硬件和任务的快速NAS方法的研究仍存在亟待解决的关键科学问题:1、NAS常被建模为奖励延迟马尔可夫决策过程,其搜索算法存在收敛速度慢的问题,研究奖励重分配的强化学习搜索算法,以加快搜索;2、目前NAS方法通常是针对单一任务定义随机初始的搜索空间,存在先验知识不足、难以快速适配不同任务的问题,针对多种任务构建具备数据和专家知识的搜索空间,实现快速适配任务的NAS方法;3、目前NAS方法通常没有考虑硬件适配问题,搜索的网络结构复杂,难以应用在资源受限的设备上,通过引入硬件约束代价,研究适配硬件的NAS方法。本课题将为NAS的落地应用奠定扎实的方法和理论基础。
英文摘要
Neural Archiitecture Search (NAS) automaticly searchs more promising architectures, which improves the study of neural network algorithm. NAS has attracted a lot of attention from scholars all over the world. However, NAS methods for edge hardwears and multiple tasks still have several problems needed to be solved: 1) NAS is usually modeled as a Markov decision process with fully delayed reward, whose search algorithm is with unstable and slow convergence. To solve this, we study reward decomposition and reward redistribution-based Reinforcement Learning (RL) search algorithm for speeding up the convergence process. 2) The search space of NAS uaually is designed only for one single task and initialized with random weights, which can't quickly adapt to different tasks. Therefore, we build a search space with data and expert knowledge for multiple tasks. 3) The current NAS methods usually do not consider the computing constraints of edge hardwares, and obtain neural networks with complex architectures and large parameters which can't apply in edge hardwares. This project aims to search neural networks for edge hardwares by introducing the computing constraints into the evaluation stratege. This project provides the theoretical foundation for the practical applicatiion of NAS methods.
期刊论文列表
专著列表
科研奖励列表
会议论文列表
专利列表
DOI:10.1007/s40747-021-00308-x
发表时间:2021-03-17
期刊:COMPLEX & INTELLIGENT SYSTEMS
影响因子:5.8
作者:Li, Nannan;Pan, Yu;Xu, Zenglin
通讯作者:Xu, Zenglin
DOI:10.1109/tcyb.2021.3078573
发表时间:2020-04
期刊:IEEE Transactions on Cybernetics
影响因子:11.8
作者:Yaran Chen;Ruiyuan Gao;Fenggang Liu;Dongbin Zhao
通讯作者:Yaran Chen;Ruiyuan Gao;Fenggang Liu;Dongbin Zhao
DOI:10.1109/tcds.2022.3230858
发表时间:2021-10
期刊:IEEE Transactions on Cognitive and Developmental Systems
影响因子:5
作者:Jiaqi Li;Haoran Li;Yaran Chen;Zixiang Ding;Nannan Li;Mingjun Ma;Zicheng Duan;Dong Zhao
通讯作者:Jiaqi Li;Haoran Li;Yaran Chen;Zixiang Ding;Nannan Li;Mingjun Ma;Zicheng Duan;Dong Zhao
DOI:10.11992/tis.202112001
发表时间:2023
期刊:智能系统学报
影响因子:--
作者:卢毅;陈亚冉;赵冬斌;刘暴;来志超;王超楠
通讯作者:王超楠
DOI:10.1109/tnnls.2021.3067028
发表时间:2021-03
期刊:IEEE Transactions on Neural Networks and Learning Systems
影响因子:10.4
作者:Zixiang Ding;Yaran Chen;Nannan Li;Dongbin Sun;C. L. P. Chen
通讯作者:Zixiang Ding;Yaran Chen;Nannan Li;Dongbin Sun;C. L. P. Chen
国内基金
海外基金
