Optimizing Performance of Convolutional Neural Network Using Computing Technique

Based on the deep learning algorithms, there are many recent rapid growths of applications. A deep learning algorithm which is expanded from Artificial Neural Networks, and it is extensively used for picture categorization and identification. Still there is no Neural Network based computing technique, i.e. pipelining has been signified in order to assist the existence of deep neural network in terms of accuracy. In this paper, Computing-based convolutional neural network system produced highly precise and productive system is used. The proposed convolutional neural network will compare with previous convolutional neural network executed on an FPGA using a computing technique to optimize the time delay and power consumption of the system, with high accuracy as compared to previous conventional neural network implementations.