2017 IEEE International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2017)

174 / 2016-12-16 13:24:47

Backpropagation Algorithm and Use of OpenMP Technique in Machine Learning -- Survey

Artificial Neural Networks (ANN), Backpropagation algorithm (BPA), Openmp, Fork-join

The Back-propagation (BP) training
algorithm is a representative of all iterative gradient
descent algorithms used for supervised learning in
neural networks. It is designed to minimize the mean
square error between the actual output of a multilayer
feed-forward neural network and the desired output.
Openmp is an important model and language extension
for shared-memory parallel programming. Openmp
offers incremental approach to parallel programming.
This paper summarizes the basic Backpropagation
Algorithm and technique of openmp to improve
backpropagation algorithm and parallelize the code for
improving the efficiency, time.