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:
“Growing up means letting go of the dearest megalomaniacal dreams of our childhood. Growing up means knowing they can’t be fulfilled. Growing up means gaining the wisdom and skills to get what we want within the limitations imposed by reality—a reality which consists of diminished powers, restricted freedoms and, with the people we love, imperfect connections.”
—Judith Viorst (20th century)
“He is no more than the chief officer of the people, appointed by the laws, and circumscribed with definite powers, to assist in working the great machine of government erected for their use, and consequently subject to their superintendence.”
—Thomas Jefferson (1743–1826)