Quantization-error-robust deep neural network for embedded accelerators

Y Jung, H Kim, Y Choi, LS Kim - IEEE Transactions on Circuits …, 2021 - ieeexplore.ieee.org
Quantization with low precision has become an essential technique for adopting deep
neural networks in energy-and memory-constrained devices. However, there is a limit to the …
被引用次数：6 相关文章

Quantization-Error-Robust Deep Neural Network for Embedded Accelerators

Y Jung, H Kim, Y Choi, LS Kim - … on Circuits and Systems II: Express …, 2022 - pure.kaist.ac.kr
Quantization with low precision has become an essential technique for adopting deep
neural networks in energy-and memory-constrained devices. However, there is a limit to the …