Deep Learning Approach for Image Classification

As of late, deep learning has gained remarkable growth in various fields, for example, computer vision and natural language processing. Contrasted with conventional machine learning strategies, deep learning has a robust learning capacity and can improve utilization of datasets for feature extraction. In view of its practicability, deep learning turns out to be increasingly mainstream for many researchers to do research works. In this paper we mainly focus on the optimization of different parameters of convolutional neural network of deep learning for classifying 8000 labelled natural images of cat and dog. First the convolutional neural network is trained to learn features then ANN binary classifier is used for classification. Various level of optimization have been done to improve the performance level of the network and finally, we achieved the best classification accuracy of 88.31%.