Sign in
SWPU: A 126.04 TFLOPS/W Edge-Device Sparse DNN Training Processor With Dynamic Sub-Structured Weight Pruning.
Yang Wang
Yubin Qin
Leibo Liu
Shaojun Wei
Shouyi Yin
Published in:
IEEE Trans. Circuits Syst. I Regul. Pap. (2022)
Keyphrases
</>
training process
avoid overfitting
high dimensional
sparse data
dynamic environments
high speed
real world
parallel processing
weighted graph
test set
read write
structured prediction
training algorithm
structured data
low cost
search space
artificial neural networks
multiscale
e learning