With the sheer size of data available today, big data brings big
opportunities and transformative potential for various sectors; on
the other hand, it also presents unprecedented challenges to harnessing
data and information. Many of the most advanced big data
applications involve the mining of heterogeneous datasets for
otherwise-obscured knowledge, patterns, and relationships.
Applying advanced machine learning algorithms and techniques
from the field of artificial intelligence. However, the current
algorithms do not scale well for big data network learning. Deep
learning is currently an extremely active research area in machine
learning and pattern recognition society. It has gained huge successes
in a broad area of applications such as speech recognition,
computer vision, and natural language processing. A novel elastic
extreme learning machine based on MapReduce framework was
proposed to cover the shortage whose learning ability was weak to
the updated large-scale training dataset [10]. Authors in [11]
proposed a novel parallel Bayesian network learning algorithm
called parallel based Bayesian network learning