Smartformer: An intelligent transformer compression framework for time-series modeling

Author:

Wang Xiaojian1,Wang Yinan2ORCID,Yang Jin1ORCID,Chen Ying1ORCID

Affiliation:

1. School of Management, Harbin Institute of Technology, Heilongjiang, China

2. Department of Industrial and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA

Funder

National Natural Science Foundation of China

Heilongjiang Natural Science Excellent Youth Fund

Publisher

Informa UK Limited

Reference38 articles.

1. Brunner C. Leeb R. Müller-Putz G. and Schlögl A. (2008) BCI competition 2008-Graz data set A . page p.6.

2. Efficient architecture search by network transformation;Cai H.;in The Thirty-Second AAAI Conference on Artificial Intelligence,2018

3. Castronovo M. Maes F. Fonteneau R. and Ernst D. (2013) Learning exploration/exploitation strategies for single trajectory reinforcement learning in European Workshop on Reinforcement Learning PMLR Press Edinburgh Scotland pp. 1–10.

4. Drone: Data-aware low-rank compression for large NLP models;Chen P.;Advances in Neural Information Processing Systems,2021

5. Cordonnier J.-B. Loukas A. and Jaggi M. (2021) Multi-head attention: Collaborate instead of concatenate. arXiv preprint arXiv:2006.16362.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3