Squeezing Correlated Neurons for Resource-Efficient Deep Neural Networks

Author:

Ozen ElbruzORCID,Orailoglu Alex

Publisher

Springer International Publishing

Reference37 articles.

1. Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), pp. 265–283 (2016)

2. Ayinde, B.O., Zurada, J.M.: Building efficient ConvNets using redundant feature pruning. arXiv:1802.07653 (2018)

3. Babaeizadeh, M., Smaragdis, P., Campbell, R.H.: NoiseOut: a simple way to prune neural networks. arXiv:1611.06211 (2016)

4. Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: IEEE International Conference on Computer Vision, pp. 2722–2730 (2015)

5. Chen, Y.H., Emer, J., Sze, V.: Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH Comput. Architect. News 44–3, 367–379 (2016)

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. Denseflex: A Low Rank Factorization Methodology for Adaptable Dense Layers in DNNs;Proceedings of the 21st ACM International Conference on Computing Frontiers;2024-05-07

2. Towards Highly Compressed CNN Models for Human Activity Recognition in Wearable Devices;2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA);2023-09-20

3. Unleashing the Potential of Sparse DNNs Through Synergistic Hardware-Sparsity Co-Design;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2023-04

4. Evolving Complementary Sparsity Patterns for Hardware-Friendly Inference of Sparse DNNs;2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD);2021-11-01

5. SNR: S queezing N umerical R ange Defuses Bit Error Vulnerability Surface in Deep Neural Networks;ACM Transactions on Embedded Computing Systems;2021-10-31

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