Deep Reinforcement Learning Agent for Dynamic Pruning of Convolutional Layers

Author:

Hadi Abir Mohammad1ORCID,Jang Youngsun1ORCID,Won Kwanghee1ORCID

Affiliation:

1. South Dakota State University, Brookings, South Dakota, USA

Publisher

ACM

Reference26 articles.

1. Using filter banks in Convolutional Neural Networks for texture classification

2. Zachary Ankner , Alex Renda , Gintare Karolina Dziugaite , Jonathan Frankle, and Tian Jin. 2022 . The Effect of Data Dimensionality on Neural Network Prunability . arXiv preprint arXiv:2212.00291 (2022). Zachary Ankner, Alex Renda, Gintare Karolina Dziugaite, Jonathan Frankle, and Tian Jin. 2022. The Effect of Data Dimensionality on Neural Network Prunability. arXiv preprint arXiv:2212.00291 (2022).

3. FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration;Chen Yanming;Knowledge-Based Systems,2022

4. Radosvet Desislavov , Fernando Martínez-Plumed , and José Hernández-Orallo . 2021. Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472 ( 2021 ). Radosvet Desislavov, Fernando Martínez-Plumed, and José Hernández-Orallo. 2021. Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472 (2021).

5. Elena Facco , Maria d' Errico , Alex Rodriguez , and Alessandro Laio . 2017. Estimating the intrinsic dimension of datasets by a minimal neighborhood information. Scientific reports 7, 1 ( 2017 ), 12140. Elena Facco, Maria d'Errico, Alex Rodriguez, and Alessandro Laio. 2017. Estimating the intrinsic dimension of datasets by a minimal neighborhood information. Scientific reports 7, 1 (2017), 12140.

Cited by 2 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. Deep Convolutional Neural Network Compression based on the Intrinsic Dimension of the Training Data;ACM SIGAPP Applied Computing Review;2024-03

2. Deep Reinforcement Learning Agent for Dynamic Pruning of Convolutional Layers;Proceedings of the International Conference on Research in Adaptive and Convergent Systems;2023-08-06

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