A 44.1TOPS/W Precision-Scalable Accelerator for Quantized Neural Networks in 28nm CMOS.
Sungju RyuHyungjun KimWooseok YiJongeun KooEunhwan KimYulhwa KimTaesu KimJae-Joon KimPublished in: CICC (2020)
Keyphrases
- neural network
- silicon on insulator
- cmos technology
- low power
- low cost
- artificial neural networks
- nm technology
- high speed
- precision and recall
- high precision
- genetic algorithm
- pattern recognition
- analog vlsi
- metal oxide semiconductor
- power consumption
- fuzzy logic
- image sensor
- fuzzy systems
- real time
- neural nets
- associative memory
- fault diagnosis
- back propagation
- parallel implementation
- recurrent neural networks
- coding scheme
- vlsi circuits
- feature vectors
- learning algorithm