153 citations · 197 across the 4 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 20 cited
Fighting Quantization Bias With Bias
Alexander Finkelstein, Uri Almog, Mark Grobman
Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network…
cs.LG2019★ 22 cited
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
Eldad Meller, Alexander Finkelstein, Uri Almog +1
Quantization of neural networks has become common practice, driven by the need for efficient implementations of deep neural networks on embedded devices. In this paper, we exploit…