An Evaluation of Deep Learning Miniature Concerning in Soft Computing

In recent years, Deep Learning at the latest developed field belonging to soft computing. The Deep learning has been a hot topic in the communities of artificial intelligence, artificial neural networks and machine learning. It tries to mimic the human brain, which is capable of processing the intricate input data, learning various knowledge’s intellectually and intense as well as solving sundry kinds of sophisticated tasks well. The deep learning paradigm tackles problems in which shallow architectures (e.g. SVM) are impressed with the curse of dimensionality. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. The transformation these characteristics of the human brain to a learning model, we wish the model can deal with the high-dimensional data, support an intense and intellectual learning algorithm and perform well in the inextricable artificial intelligence, real tasks, such as pattern recognition speech recognition, image classification, computer vision and natural language processing. In this paper, we are discussing the history of deep learning, Deep Learning Architectures, abridge the components of Deep Boltzmann Machines (DBM), Deep Stacking Networks (DSN), Compound Hierarchical Deep Models(CHDM), Deep Convolutional Neural Network (DCNN) and Deep Belief Network (DBN) their learning algorithms.