Calibrating process variation at system level with in-situ low-precision transfer learning for analog neural network processors
2018 55TH ACM/ESDA/IEEE DESIGN AUTOMATION CONFERENCE (DAC)(2018)
摘要
Process Variation (PV) may cause accuracy loss of the analog neural network (ANN) processors, and make it hard to be scaled down, as well as feasibility degrading. This paper first analyses the impact of PV on the performance of ANN chips. Then proposes an in-situ transfer learning method at system level to reduce PV's influence with low-precision back-propagation. Simulation results show the proposed method could increase 50% tolerance of operating point drift and 70% ∼ 100% tolerance of mismatch with less than 1% accuracy loss of benchmarks. It also reduces 66.7% memories and has about 50× energy-efficiency improvement of multiplication in the learning stage, compared with the conventional full-precision (32bit float) training system.
更多查看译文
关键词
Analog Neural Network, Process Variation, Low-Precision, In-Situ Transfer Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络