Record Details

Stochastic Computing Correlation Utilization in Convolutional Neural Network Basic Functions

UAD Journal Management System

View Archive Info
 
 
Field 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