Method for Hybrid Precision Convolutional Neural Network Representation

This invention addresses fixed-point representations of convolutional neural networks (CNN) in integrated circuits. When quantizing a CNN for a practical implementation there is a trade-off between the precision used for operations between coefficients and data and the accuracy of the system. A homo...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-07
Main Authors: Al-Hami, Mo'taz, Pietron, Marcin, Kumar, Rishi, Casas, Raul A, Hijazi, Samer L, Rowen, Chris
Format: Article
Language:English
Subjects:
Artificial neural networks
Counting
Integrated circuits
Neural networks
Power consumption
Power efficiency
Representations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This invention addresses fixed-point representations of convolutional neural networks (CNN) in integrated circuits. When quantizing a CNN for a practical implementation there is a trade-off between the precision used for operations between coefficients and data and the accuracy of the system. A homogenous representation may not be sufficient to achieve the best level of performance at a reasonable cost in implementation complexity or power consumption. Parsimonious ways of representing data and coefficients are needed to improve power efficiency and throughput while maintaining accuracy of a CNN.
ISSN:2331-8422