A Time-Domain Binary CNN Engine With Error-Detection-Based Resilience in 28nm CMOS

IEEE Transactions on Circuits and Systems II: Express Briefs(2021)

引用 4|浏览2
暂无评分
摘要
Due to the increasing demand of high energy-efficient processor for deep neural networks, traditional neural network engines with high-precision weights and activations that usually occupies huge on/off-chip resources with large power consumption are no longer suitable for Internet-of-Things applications. Binary neural networks (BNNs) reduce memory size and computation complexity, achieving drasti...
更多
查看译文
关键词
Engines,Neural networks,Energy efficiency,Convolution,Delays,Hardware,Time-domain analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要