Assessment of Accuracy Enhancement of Back Propagation Algorithm by Training the Model using Deep Learning

Abstract

Deep learning is a branch of machine learning which is recently gaining a lot of attention due to its efficiency in solving a number of AI problems. The aim of this research is to assess the accuracy enhancement by using deep learning in back propagation algorithm. For this purpose, two techniques has been used. In the first technique, simple back propagation algorithm is used and the designed model is tested for accuracy. In the second technique, the model is first trained using deep learning via deep belief nets to make it learn and improve its parameters values and then back propagation is used over it. The advantage of softmax function is used in both the methods. Both the methods have been tested over images of handwritten digits and accuracy is then calculated. It has been observed that there is a significant increase in the accuracy of the model if we apply deep learning for training purpose.