Restricted Boltzmann Machine

Page numbers are for draft copy at present; they will be replaced with correct numbers when final book is formatted. Chapter numbers are correct and will not change now.

A Restricted Boltzmann Machine (RBM) is a form of Boltzmann machine where input and output layers are fully connected to each another, but have no internal connections. That is gthere are no input-input, not output-output links. Otherwsie they are like a standard {{Boltzmann Machine} } with a training phase with inputs clamped and outputs free to vary and then a recall mode where some inputs are clamped and the network fills in the gaps. As well as this reocnstreuction mode, RBMs are often used for feature detction in the early stages of deep neaural networks as they use feedforward learning rather than backpropagation. The Restricted Boltzmann Machine (RBM) like the Boltzmann machine is a form of neural network and autoencoder.

Used on Chap. 6: page 120; Chap. 8: page 155; Chap. 10: page 209; Chap. 12: page 278

Also known as RBM