Deep Machine Learning and Neural Networks: An Overview

Chandrahas Mishra, Dharmendra Lal Gupta
2016 International Journal of Hybrid Information Technology  
Deep learning is a technique of machine learning in artificial intelligence area. Deep learning is a refined "machine learning" algorithm that surpasses a considerable lot of its forerunners in its capacity to perceive syllables and pictures. As of now Deep learning is a greatly dynamic examination territory in machine learning and example acknowledgment society. It has increased colossal triumphs in an expansive zone of utilizations, for example, speech recognition, computer vision and natural
more » ... language processing and numerous industry items. Neural networks are used to implement the machine learning or to design intelligent machines. In this paper thorough survey to all machine learning paradigms and application areas of deep machine learning and different types of neural networks with applications are discussed. Deep learning refers to a class of ML techniques, where numerous layers of data processing stages in various leveled architectures are exploited for unsupervised feature learning and for pattern classification. It is in the convergences among the research area of neural system, optimization, graphical modelling, signal processing, and pattern recognition. Two vital explanations behind the prominence of deep learning today are the fundamentally brought down expense of processing equipment and the drastically increased chip processing abilities e.g., GPU units. Success of deep learning in various applications including computer vision, phonetic recognition, voice search, spontaneous speech recognition, speech and image feature coding, semantic utterance classification, hand-writing recognition, audio processing, information retrieval, and robotics and many artificial intelligence area. Before going to deal with different machine learning paradigm in detail, a brief classification is shown in Figure 1 . We use four key attribute to classify the machine learning paradigm 1 2 -
doi:10.14257/ijhit.2016.9.11.34 fatcat:tvbfxbm5pnea5bjsjy5w7t3jem