CNN Inference Using a Preprocessing Precision Controller and Approximate Multipliers With Various Precisions

CNN Inference Using a Preprocessing Precision Controller and Approximate Multipliers With Various Precisions

This article proposes boosting the multiplication performance for convolutional neural network (CNN) inference using a precision prediction preprocessor which controls various precision approximate multipliers. Previously, utilizing approximate multipliers for CNN inference was proposed to enhance t...

Full description

Bibliographic Details
Main Authors: Issam Hammad, Ling Li, Kamal El-Sankary, W. Martin Snelgrove
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Approximate computing
approximate multiplier
CNN accelerator
deep learning
reconfigurable approximate multiplier
precision prediction
Online Access:https://ieeexplore.ieee.org/document/9313992/

Internet

https://ieeexplore.ieee.org/document/9313992/

Similar Items