上海交大研究生院主页平台管理系统何哲陟--中文主页-- Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point

论文成果

当前位置: 中文主页 >> 科学研究 >> 论文成果 >> Improving Neural ...

Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point

上一条： CMP-PIM: an energy efficient comparator-based processing-in-memory neural network accelerator

下一条： KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning