Introduction to Deep Learning

Abstract

Deep learning has gained increasing attention in automatic speech recognition, computer vision, natural language processing, drug discovery toxicology, audio recognition, bioinformatics, and automatic driving of vehicles due to its potential benefits such as feature extraction and data classification problems. It is an evolving research domain in diverse applications which increases the overall potential cost benefits for maintenance and refurbishes activities. Deep learning is an ubiquitous technology, and the machine learning algorithms assist in modelling high-level abstract view of data by means of processing layers which encompasses complex structures. The software tools in this area provide finer representations from massive volume of unlabeled data. The software in deep learning identifies patterns in the form of digital representation such as images, data, sound, etc. According to Gartner’s hype cycle, deep learning is on “permanent peak” since 2015, and HFS research survey states that 86% of respondents believe that the technology makes a huge business impact in the industry sector. It is a rapid growing domain with a set of powerful techniques and huge amount of computational power, where machine identifies objects and translates the recognized speech in real time. The main key aspects of deep learning are (i) models comprising several stages or layers of nonlinear information processing and (ii) methodologies for supervised or unsupervised learning for feature extraction at an abstraction level. The significant reasons for its popularity are the increased size of training data set, chip processing capabilities, and the recent advancement in signal processing and machine learning research. The deep learning techniques are effectually exploiting intricate nonlinear functions to acquire hierarchical and distributed feature representations in the perspective of utilizing both labeled and unlabeled data. The different deep learning methods and architectures such as convolutional deep neural network (CDNN), deep neural network (DNN), recurrent neural network (RNN), deep belief network (DBN), artificial neural network (ANN), and long short-term memory (LSTM) are discussed.