Restricted Boltzmann Machine
Although learning is impractical in general Boltzmann machines, it can be made quite efficient in an architecture called the "restricted Boltzmann machine" or "RBM" which does not allow intralayer connections between hidden units. After training one RBM, the activities of its hidden units can be treated as data for training a higher-level RBM. This method of stacking RBM's makes it possible to train many layers of hidden units efficiently and is one of the most common deep learning strategies. As each new layer is added the overall generative model gets better.
There is an extension to the restricted Boltzmann machine that affords using real valued data rather than binary data. Along with higher order Boltzmann machines, it is outlined here .
One example of a practical application of Restricted Boltzmann machines is the performance improvement of speech recognition software.
Read more about this topic: Boltzmann Machine
Famous quotes containing the words restricted and/or machine:
“One thing that literature would be greatly the better for
Would be a more restricted employment by authors of simile and
metaphor.”
—Ogden Nash (1902–1971)
“The cycle of the machine is now coming to an end. Man has learned much in the hard discipline and the shrewd, unflinching grasp of practical possibilities that the machine has provided in the last three centuries: but we can no more continue to live in the world of the machine than we could live successfully on the barren surface of the moon.”
—Lewis Mumford (1895–1990)