Research paper / RESOURCE PROFILE

1712-Quantization and Training of Neural Networks for Efficient Intege

Publication: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Published Dec 15, 2017.

AI Trading & Research
arxiv.orgPublished Dec 15, 2017
Visit source website ↗
Screenshot unavailableResource information and source links remain available. 1712-Quantization and Training of Neural Networks for Efficient Intege — reviewed source website screenshot
Reviewed source screenshot · recorded Oct 11, 2026 View source ↗

Overview

Publication: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Published Dec 15, 2017.

Publication information

Publication title
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Authors
Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, Dmitry Kalenichenko
Published
Dec 15, 2017
Last publication revision
Dec 15, 2017
Subject areas
cs.LG, stat.ML
Publication source
arxiv.org · abs/1712.05877v1 ↗

Source: arXiv API · observed Oct 11, 2026.

Source links & provenance

https://arxiv.org/abs/1712.05877 ↗

Discovery references

References explain how this resource entered the collection. They do not represent an endorsement.

Explore related resources

Sign In

Don't have an account yet? Register

Forgot password?

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.