Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning

Published:2023-04 Issue: Volume:38 Page:100857
ISSN:2210-5379
Container-title:Sustainable Computing: Informatics and Systems
language:en
Short-container-title:Sustainable Computing: Informatics and Systems

Author:

Desislavov Radosvet,Martínez-Plumed Fernando^ORCID,Hernández-Orallo José^ORCID

Publisher

Elsevier BV

Subject

Electrical and Electronic Engineering,General Computer Science

Reference112 articles.

1. Great power, great responsibility: Recommendations for reducing energy for training language models;McDonald,2022

2. Google cloud doubles down on nvidia gpus for inference;Freund,2019

3. Ai and Efficiency;Hernandez,2020

4. Amazon ec2 update-infl instances with aws inferentia chips for high performance cost-effective inferencing;Barr,2019

5. Aws to offer nvidia’s t4 gpus for ai inferencing;Leopold,2019

Cited by 56 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A novel green learning artificial intelligence model for regional electrical load prediction;Expert Systems with Applications;2024-12

2. Computer-assisted analysis of routine EEG to identify hidden biomarkers of epilepsy: A systematic review;Computational and Structural Biotechnology Journal;2024-12

3. CANSat-IDS: An adaptive distributed Intrusion Detection System for satellites, based on combined classification of CAN traffic;Computers & Security;2024-11

4. A CNN pruning approach using constrained binary particle swarm optimization with a reduced search space for image classification;Applied Soft Computing;2024-10

5. AI Coders Are among Us: Rethinking Programming Language Grammar towards Efficient Code Generation;Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis;2024-09-11

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