Scalable Neural Network Using Hadoop and MapReduce

Abstract

With the advent of digital technology, a large amount of digital data is being generated every day. One of the challenges is the volume of generated data. Because of the massive increase in the size of the data it becomes troublesome to perform effective analysis using the current traditional techniques. Artificial Neural Network (ANN) is widely used algorithm in classification, pattern recognition and prediction fields. However, ANNs are notably slow in computation especially when the size of data is large. To fulfill the potentials of ANNs for big data applications, the computation process must be speedup. The objective of this paper is to classify big data using Back-propagation Neural Network method with MapReduce paradigm which has become a major computing model to facilitate data intensive applications. The performance is measured by the execution time using two different interesting datasets. And the results show that proposed algorithm performs superior efficiency (time) better than single node Java implementation that do not use Hadoop and MapReduce.