Standalone 16-bit precision neural network training matches the accuracy of 32-bit and mixed-precision training while increasing computational speed.
Efficient deep learning inference on embedded systems using fixed-point arithmetic on fpgas.Journal of Signal Processing Systems, 91(1):1–13
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning
Standalone 16-bit precision neural network training matches the accuracy of 32-bit and mixed-precision training while increasing computational speed.