专利名称：COMPUTER-IMPLEMENTED METHODS AND SYSTEMS FOR COMPRESSING DEEP NEURAL
NETWORK MODELS USING ALTERNATING
DIRECTION METHOD OF MULTIPLIERS
sch
针灸英语(ADMM)
发明人：Yanzhi Wang,Xue Lin
64届艾美奖
申请号：US17128763
申请日：20201221
公开号：US20210192352A1
公开日：
20210624
专利内容由知识产权出版社提供怎么搭配服装
专利附图：onenote是什么
摘要：ADMM-NN is an algorithm-hardware co-optimization framework of DNNs using Alternating Direction Method of Multipliers (ADMM). The first part of ADMM-NN is a systematic, joint framework of DNN weight pruning and quantization using ADMM. The cond part is a hardware-aware optimization to facilitate hardware-level implementations. ADMM-bad weight pruning and quantization accounts for (i) computation reduction and energy efficiency improvement and (ii) performance overhead due to irregular sparsity. Experimental results demonstrate that by combining weight pruning and quantization, the propod framework can achieve 1,910× and 231×reductions in the overall model size on the LeNet-5 and AlexNet models. Favorable results are also obrved on VGGNet and ResNet models. Also, without any accuracy loss, 3.6× reduction in the amount of computation can be achieved, outperforming prior work.
佳能广告曲申请人：Northeastern University
地址：Boston MA USint>小学一年级英语上册
国籍：US
更多信息请下载全文后查看bugreport>body是什么意思
