Embedded 1-Mb ReRAM-Based Computing-in- Memory Macro With Multibit Input and Weight for CNN-Based AI Edge Processors.
Cheng-Xin XueTing-Wei ChangTung-Cheng ChangHui-Yao KaoYen-Cheng ChiuChun-Ying LeeYa-Chin KingChrong Jung LinRen-Shuo LiuChih-Cheng HsiehKea-Tiong TangWei-Hao ChenMeng-Fan ChangJe-Syu LiuJia-Fang LiWei-Yu LinWei-En LinJing-Hong WangWei-Chen WeiTsung-Yuan HuangPublished in: IEEE J. Solid State Circuits (2020)
Keyphrases
- artificial intelligence
- embedded processors
- embedded systems
- expert systems
- memory subsystem
- parallel algorithm
- machine learning
- case based reasoning
- input data
- parallel processing
- computational power
- memory hierarchy
- multithreading
- processing elements
- cellular neural networks
- computing power
- edge weights
- ai systems
- neural network
- memory management
- weighted graph
- memory requirements
- times faster
- multicore processors
- knowledge representation
- dynamic random access memory