A 1.625 TOPS/W SOC for Deep CNN Training and Inference in 28nm CMOS.
Yu-Tung LiuChuKing KungMing-Hang HsiehHsiu-Wen WangChun-Pin LinChao-Yang YuChi-Shi ChenTzi-Dar ChiuehPublished in: ESSCIRC (2021)
Keyphrases
- low power
- structured prediction
- low cost
- high speed
- cmos technology
- training samples
- power consumption
- cellular neural networks
- bayesian inference
- deep architectures
- test set
- training algorithm
- belief nets
- decision trees
- vlsi circuits
- training process
- probabilistic inference
- belief networks
- training examples
- training set
- bayesian networks