Post-Training BatchNorm Recalibration

10/12/2020
by   Gil Shomron, et al.
0

We revisit non-blocking simultaneous multithreading (NB-SMT) introduced previously by Shomron and Weiser (2020). NB-SMT trades accuracy for performance by occasionally "squeezing" more than one thread into a shared multiply-and-accumulate (MAC) unit. However, the method of accommodating more than one thread in a shared MAC unit may contribute noise to the computations, thereby changing the internal statistics of the model. We show that substantial model performance can be recouped by post-training recalibration of the batch normalization layers' running mean and running variance statistics, given the presence of NB-SMT.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

03/05/2018

OpenMath and SMT-LIB

OpenMath and SMT-LIB are languages with very different origins, but both...
04/17/2020

Non-Blocking Simultaneous Multithreading: Embracing the Resiliency of Deep Neural Networks

Deep neural networks (DNNs) are known for their inability to utilize und...
05/07/2021

lazybvtoint at the SMT Competition 2020

lazybvtoint is a new prototype SMT-solver, that will participate in the ...
09/01/2018

MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

This paper describes the Microsoft and University of Edinburgh submissio...
06/13/2019

Astra Version 1.0: Evaluating Translations from Alloy to SMT-LIB

We present a variety of translation options for converting Alloy to SMT-...
03/07/2021

Translating the Unseen? Yorùbá → English MT in Low-Resource, Morphologically-Unmarked Settings

Translating between languages where certain features are marked morpholo...
10/26/2019

DDM: A Demand-based Dynamic Mitigation for SMT Transient Channels

Different from the traditional software vulnerability, the microarchitec...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.