AME: Attention and Memory Enhancement in Hyper-Parameter Optimization | |
Xu, Nuo2,3; Chang, Jianlong1; Nie, Xing2,3; Huo, Chunlei2,3; Xiang, Shiming2,3; Pan, Chunhong2,3 | |
2022 | |
会议日期 | 2022.6.19-6.24 |
会议地点 | New Orleans, USA |
英文摘要 | Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation. To solve these two difficulties, an efficient parallel hyper-parameter optimization model is proposed under the framework of Deep Reinforcement Learning (DRL). Technically, we develop Attention and Memory Enhancement (AME), that includes multi-head attention and memory mechanism to enhance the ability to capture both the short-term and long-term relationships between different hyper-parameter configurations, yielding an attentive sampling mechanism for searching high-performance configurations embedded into a huge search space. During the optimization of transformer-structured configuration searcher, a conceptually intuitive yet powerful strategy is applied to solve the problem of insufficient number of samples due to the untimely feedback. Experiments on three visual tasks, including image classification, object detection, semantic segmentation, demonstrate the effectiveness of AME. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/50608] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Huo, Chunlei |
作者单位 | 1.Huawei Cloud & AI 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.NLPR, Institute of Automation, Chinese Academy of Sciences, |
推荐引用方式 GB/T 7714 | Xu, Nuo,Chang, Jianlong,Nie, Xing,et al. AME: Attention and Memory Enhancement in Hyper-Parameter Optimization[C]. 见:. New Orleans, USA. 2022.6.19-6.24. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论