A review of deep learning architectures and their application

Abstract

Deep Learning is a new era of machine learning research that are making major advances in solving problem with powerful computational models. Currently, this new machine learning method is widely used in object detection, visual object and speech recognition and also for making prediction of regulatory genomic and cellular imaging. Here, we review the methodology and applications of deep learning architectures including deep neural network, convolutional neural network and recurrent neural network. Next, we review several existing prediction tools in genomic sequences analysis that use deep learning architectures. In addition, we discuss the future research directions of deep learning.