Parallel Backpropagation Neural Network Training Techniques using Graphics Processing Unit
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 2
Abstract
Training of artificial neural network using back-propagation is a computational expensive process in machine learning. Parallelization of neural networks using Graphics Pro-cessing Unit (GPU) can help to reduce the time to perform computations. GPU uses a Single Instruction Multiple Data (SIMD) architecture to perform high speed computing. The use of GPU shows remarkable performance gain when compared to CPU. This work discusses different parallel techniques for the backpropagation algorithm using GPU. Most of the techniques perform comparative analysis between CPU and GPU.
Authors and Affiliations
Muhammad Arslan Amin, Muhammad Kashif Hanif, Muhammad Umer Sarwar, Abdur Rehman, Fiaz Waheed, Haseeb Rehman
Keywords
Related Articles
- EP ID EP468733
- DOI 10.14569/IJACSA.2019.0100270
- Views 98
- Downloads 0
Estimation Method of Ionospheric TEC Distribution using Single Frequency Measurements of GPS Signals
The satellite-to-ground communications are influenced by ionospheric plasma which varies depending on solar and geomagnetic activities as well as regions and local times. With the expansion of use of the space, continuou...
Enhanced and Improved Hybrid Model to Prediction of User Awareness in Agriculture Sector
Agriculture is the backbone of Indian economy and is the main income source for most of the population in India. So farmers are always curious about yield prediction. Crop yield depends on various factors like soil, weat...
Using Space Syntax and Information Visualization for Spatial Behavior Analysis and Simulation
This study used space syntax to discuss user movement dynamics and crowded hot spots in a commercial area. Moreover, it developed personas according to its onsite observations, visualized user movement data, and performe...
Reflected Adaptive Differential Evolution with Two External Archives for Large-Scale Global Optimization
JADE is an adaptive scheme of nature inspired algorithm, Differential Evolution (DE). It performed considerably improved on a set of well-studied benchmark test problems. In this paper, we evaluate the performance of new...
BF-PSO-TS: Hybrid Heuristic Algorithms for Optimizing Task Schedulingon Cloud Computing Environment
Task Scheduling is a major problem in Cloud computing because the cloud provider has to serve many users. Also, a good scheduling algorithm helps in the proper and efficient utilization of the resources. So, task schedul...