Evaluating the merits of ranking in structured network pruning

• Main Authors: Sharma, Kuldeep, Ramakrishnan, Nirmala, Prakash, Alok, Lam, Siew-Kei, Srikanthan, Thambipillai
• 其他作者: School of Computer Science and Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2021
• 主題: Engineering::Computer science and engineering; Neural Networks; Structured Pruning
• 在線閱讀: https://hdl.handle.net/10356/147716
• 機構: Nanyang Technological University

Pruning of channels in trained deep neural networks has been widely used to implement efficient DNNs that can be deployed on embedded/mobile devices. Majority of existing techniques employ criteria-based sorting of the channels to preserve salient channels during pruning as well as to automatically...