アメリカのコンピューター科学工学ジャーナル の調査 オープンアクセス

抽象的な

Extensive Deep Belief Nets with Restricted Boltzmann Machine Using MapReduce Framework

Pandiganesh S. and J.C. Miraclin Joyce Pamila

Extensive Deep Belief Nets with Restricted Boltzmann Machine Using MapReduce Framework

Big data is a collection of data sets which is used to describe the exponential growth and availability of both ordered and amorphous data. It is difficult to process big data using traditional data processing applications. In many practical problems, deep learning is one of the machine learning algorithms that has received great popularity in both academia and industry due to its high-level abstractions in data by using model architectures. In deep learning, Deep Belief Nets are stacks for restricted Boltzmann Machine and it is the most important deep layered (multi-layer) architecture. A restricted Boltzmann Machine is the energy based models for pretraining and followed by fine-tuning the whole net using back propagation. This mainly involves the process of classification of data. This paper contains a survey about Deep Belief Nets (DBNs) which is composed of multiple layers of latent variables along with stacked restricted Boltzmann Machine and describes big data processing. The survey concludes that the learning of Deep Belief Nets (DBNs) has attracted widespread attention due to their efficient performance in various applications.