Jump-GRS:

Xiaomin Wu1,2, Da-Ting Lin3, Rong Chen2

  • 1Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, United States of America.

PubMed
概括

一个新的算法,跳跃贪的层间顺序随机选择 (JGRS),显著加快神经解码模型的压缩速度. JGRS实现了与GRS相比较的模型紧性,但修剪速度快2至8倍.