Tech moves fast! Stay ahead of the curve with Techopedia!
Join nearly 200,000 subscribers who receive actionable tech insights from Techopedia.
A deep belief network (DBN) is a sophisticated type of generative neural network that uses an unsupervised machine learning model to produce results. This type of network illustrates some of the work that has been done recently in using relatively unlabeled data to build unsupervised models.
Some experts describe the deep belief network as a set of restricted Boltzmann machines (RBMs) stacked on top of one another. In general, deep belief networks are composed of various smaller unsupervised neural networks. One of the common features of a deep belief network is that although layers have connections between them, the network does not include connections between units in a single layer.
Geoff Hinton, one of the pioneers of this process, characterizes stacked RBMs as providing a system that can be trained in a “greedy” manner and describes deep belief networks as models “that extract a deep hierarchical representation of training data.”
In general, this type of unsupervised machine learning model shows how engineers can pursue less structured, more rugged systems where there is not as much data labeling and the technology has to assemble results based on random inputs and iterative processes.