An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM.
Geng YuanXiaolong MaCaiwen DingSheng LinTianyun ZhangZeinab S. JalaliYilong ZhaoLi JiangSucheta SoundarajanYanzhi WangPublished in: CoRR (2019)