Tech moves fast! Stay ahead of the curve with Techopedia!
Join nearly 200,000 subscribers who receive actionable tech insights from Techopedia.
A restricted Boltzmann machine (RBM) is a type of artificial neural network invented by Geoff Hinton, a pioneer in machine learning and neural network design.
This type of generative network is useful for filtering, feature learning and classification, and it employs some types of dimensionality reduction to help tackle complicated inputs.
The restricted Boltzmann machine is so-called because there is no communication between layers in the model, which is the “restriction” of the model. Experts explain that RBM nodes make “stochastic” decisions, or that these are randomly determined. Various weights change the structure of the input, and activation functions process the output of a node. Like other types of similar systems, the restricted Boltzmann machine operates with input layers, hidden layers and output layers to achieve machine learning results. The RBM has also been useful in creating more sophisticated models, such as deep belief networks, by stacking individual RBMs together.