Stochastic Computing Correlation Utilization in Convolutional Neural Network Basic Functions
UAD Journal Management System
View Archive InfoField | Value | |
Authentication Code |
dc |
|
Title Statement |
Stochastic Computing Correlation Utilization in Convolutional Neural Network Basic Functions |
|
Added Entry - Uncontrolled Name |
Abdellatef, Hamdan; Universiti Teknologi Malaysia Hani, Mohamed Khalil; Universiti Teknologi Malaysia Husin, Nasir Shaikh; Universiti Teknologi Malaysia Ayat, Sayed Omid; Universiti Teknologi Malaysia |
|
Uncontrolled Index Term |
convolutional neural network; stochastic computing; correlation; |
|
Summary, etc. |
In recent years, many applications have been implemented in embedded systems and mobile Internet of Things (IoT) devices that typically have constrained resources, smaller power budget, and exhibit "smartness" or intelligence. To implement computation-intensive and resource-hungry Convolutional Neural Network (CNN) in this class of devices, many research groups have developed specialized parallel accelerators using Graphical Processing Units (GPU), Field-Programmable Gate Arrays (FPGA), or Application-Specific Integrated Circuits (ASIC). An alternative computing paradigm called Stochastic Computing (SC) can implement CNN with low hardware footprint and power consumption. To enable building more efficient SC CNN, this work incorporates the CNN basic functions in SC that exploit correlation, share Random Number Generators (RNG), and is more robust to rounding error. Experimental results show our proposed solution provides significant savings in hardware footprint and increased accuracy for the SC CNN basic functions circuits compared to previous work. |
|
Publication, Distribution, Etc. |
Universitas Ahmad Dahlan 2018-12-01 00:00:00 |
|
Electronic Location and Access |
application/pdf http://journal.uad.ac.id/index.php/TELKOMNIKA/article/view/8955 |
|
Data Source Entry |
TELKOMNIKA (Telecommunication Computing Electronics and Control); Vol 16, No 6: December 2018 |
|
Language Note |
en |
|
Terms Governing Use and Reproduction Note |
Copyright (c) 2020 Universitas Ahmad Dahlan |
|