On the Performance of Parallel Back-propagation Neural Network Implementations Using CUDA

نویسندگان

  • K Ganeshamoorthy
  • Nagulan Ratnarajah
چکیده

In this paper, we study the impact of the many core Graphics Processing Units (GPUs) system on the implementation of parallel algorithm for back-propagation neural network training. We provide a comparison between the running times taken on the GPU and on the conventional CPU to perform the training of a back-propagation neural network. We design and implement a back-propagation neural network training algorithms to predict the exchange fluctuation rate as determined by demand and supply conditions in the foreign exchange market. The Compute Unified Device Architecture (CUDA C) is used to implement the parallel version of training algorithm running on GPU and the C language is used to implement the serial version of training algorithm running on conventional CPU. The system will use past historical data, while training. Our results confirm the speed-up advantages by tapping on the resources of GPU. keywords: neural network, back-propagation, multicore, CUDA

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Predicting air pollution in Tehran: Genetic algorithm and back propagation neural network

Suspended particles have deleterious effects on human health and one of the reasons why Tehran is effected is its geographically location of air pollution. One of the most important ways to reduce air pollution is to predict the concentration of pollutants. This paper proposed a hybrid method to predict the air pollution in Tehran based on particulate matter less than 10 microns (PM10), and the...

متن کامل

Application of Linear Regression and Artificial NeuralNetwork for Broiler Chicken Growth Performance Prediction

This study was conducted to investigate the prediction of growth performance using linear regression and artificial neural network (ANN) in broiler chicken. Artificial neural networks (ANNs) are powerful tools for modeling systems in a wide range of applications. The ANN model with a back propagation algorithm successfully learned the relationship between the inputs of metabolizable energy (kca...

متن کامل

MPI- and CUDA- implementations of modal finite difference method for P-SV wave propagation modeling

Among different discretization approaches, Finite Difference Method (FDM) is widely used for acoustic and elastic full-wave form modeling. An inevitable deficit of the technique, however, is its sever requirement to computational resources. A promising solution is parallelization, where the problem is broken into several segments, and the calculations are distributed over different processors. ...

متن کامل

A Novel Method for Iris Recognition Using BP Neural Network and Parallel Computing

In this paper, we seek a new method in designing an iris recognition system. In this method, first the Haar wavelet features are extracted from iris images. The advantage of using these features is the high-speed extraction, as well as being unique to each iris. Then the back propagation neural network (BPNN) is used as a classifier. In this system, the BPNN parallel algorithms and their implem...

متن کامل

On the use of back propagation and radial basis function neural networks in surface roughness prediction

Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017