Deep learning is a new era of machine learning and belonging to the area of artificial intelligence. It has tried to mimic the working of the way the human brain does. The models of deep learning have the capability to deal with high dimensional data and perform the complicated tasks in an accurate manner with the use of graphical processing unit (GPU). Significant performance is observed to analyze images, videos, text and speech. This paper deals with the detailed comparison of various deep learning models and the area in which these various deep learning models can be applied. We also present the comparison of various deep networks of classification. The paper also describes deep learning libraries along with the platform and interface in which they can be used. The accuracy is evaluated with respect to various machine learning and deep learning models on the MNIST dataset. The evaluation shows classification on deep learning model is far better than a machine learning model.
CITATION STYLE
Garg, D., Goel, P., Kandaswamy, G., Ganatra, A., & Kotecha, K. (2019). A roadmap to deep learning: A state-of-the-art step towards machine learning. In Communications in Computer and Information Science (Vol. 955, pp. 160–170). Springer Verlag. https://doi.org/10.1007/978-981-13-3140-4_15
Mendeley helps you to discover research relevant for your work.