Fig. 4From: Granular computing with multiple granular layers for brain big data processingExample of RBMs and graphic model of a deep belief network based on RBMs. a Pretraining consists of learning a stack of RBMs, each having only one layer of feature detectors [62] and b graphical model of a deep belief network with observed vector x and hidden layers h1, h2 and h3 [63]Back to article page