A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Mixed-precision weights network for field-programmable gate array
2021
PLoS ONE
In this study, we introduced a mixed-precision weights network (MPWN), which is a quantization neural network that jointly utilizes three different weight spaces: binary {−1,1}, ternary {−1,0,1}, and 32-bit floating-point. We further developed the MPWN from both software and hardware aspects. From the software aspect, we evaluated the MPWN on the Fashion-MNIST and CIFAR10 datasets. We systematized the accuracy sparsity bit score, which is a linear combination of accuracy, sparsity, and number
doi:10.1371/journal.pone.0251329
pmid:33970965
pmcid:PMC8109814
fatcat:v5svfwclxjhaxf5bkrfdrwaiqu