A 1.23μJ/Inference, All-Digital Shuffle-Type Group-CNN Accelerator in 28nm CMOS With 85.8% Accuracy on CIFAR-10.
Long ChenCai LiTao WangJunyi QianWeiwei ShanPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2023)
Keyphrases
- circuit design
- power consumption
- high speed
- computational cost
- metal oxide semiconductor
- prediction accuracy
- high accuracy
- classification accuracy
- low cost
- bayesian networks
- group members
- convolutional neural network
- cmos image sensor
- error rate
- computational efficiency
- digital camera
- low power
- image processing algorithms
- inference process
- single chip
- transmission electron microscopy