登录 注册 会员服务 联系我们

Building High-throughput Neural Architecture Search Workflows via a Decoupled Fitness Prediction Engine

  • Published:2022 Issue: Volume: Page:1-1
  • ISSN:1045-9219
  • Container-title:IEEE Transactions on Parallel and Distributed Systems
  • language:
  • Short-container-title:IEEE Trans. Parallel Distrib. Syst.

Author:

Keller Rorabaugh Ariel,Caino-Lores Silvina,Johnston Travis,Taufer Michela

Funder

Department of Energy DoE

National Science Foundation

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Signal Processing

Reference55 articles.

1. Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy;scheidegger;Comput Vis,2020

2. Cinic-10 is not imagenet or cifar-10;darlow,2018

3. DENSER: deep evolutionary network structured representation

4. Deep variance network: An iterative, improved CNN framework for unbalanced training datasets

5. Batch-normalized Mlpconv-wise supervised pre-training network in network

Cited by 5 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. VINARCH: A Visual Analytics Interactive Tool for Neural Network Archaeology;2023 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops);2023-10-31

2. Composable Workflow for Accelerating Neural Architecture Search Using In Situ Analytics for Protein Classification;Proceedings of the 52nd International Conference on Parallel Processing;2023-08-07

3. A Methodology to Generate Efficient Neural Networks for Classification of Scientific Datasets;2022 IEEE 18th International Conference on e-Science (e-Science);2022-10

4. Identifying Structural Properties of Proteins from X-ray Free Electron Laser Diffraction Patterns;2022 IEEE 18th International Conference on e-Science (e-Science);2022-10

5. High frequency accuracy and loss data of random neural networks trained on image datasets;Data in Brief;2022-02
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