An Overview of Techniques, Applications of Deep Learning Algorithms with Deep Neural Network (Dnn) Architectures

Abstract

Deep Neural Networks (DNNs) have emerged as a viable method for incorporating deep learning into our daily lives via self-driving cars, smartphones, gaming, and drones, among other applications. Deep learning algorithms have also been successfully used to computer vision, pattern recognition, audio recognition, natural language processing, and recommendation systems. One of the advantages of deep learning is its capacity to learn from vast amounts of data. The domain of deep learning has evolved rapidly in recent years, and it has been successfully applied to a wide variety of traditional applications. As a result, techniques that enable effective DNN processing in order to increase energy economy and throughput without reducing application accuracy or increasing hardware costs are crucial for DNNs to be widely deployed in AI systems. As such, we propose in this contribution to take a more holistic approach in order to provide a more appropriate beginning point for developing a comprehensive understanding of DL. Specifically, this review aims to provide a more detailed overview of the most critical features of DL, as well as current advancements in the area.