NAND-SPIN-based processing-in-MRAM architecture for convolutional neural network acceleration.
Yinglin ZhaoJianlei YangBing LiXingzhou ChengXucheng YeXueyan WangXiaotao JiaZhaohao WangYouguang ZhangWeisheng ZhaoPublished in: Sci. China Inf. Sci. (2023)
Keyphrases
- convolutional neural network
- design considerations
- real time
- parallel architecture
- distributed processing
- management system
- network architecture
- processing units
- information processing
- software architecture
- processing elements
- data processing
- neural network
- face detection
- low cost
- object detection
- computer vision
- machine learning
- memory management
- computation intensive