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:
“Language can only deal meaningfully with a special, restricted segment of reality. The rest, and it is presumably the much larger part, is silence.”
—George Steiner (b. 1929)
“What is man, when you come to think upon him, but a minutely set, ingenious machine for turning, with infinite artfulness, the red wine of Shiraz into urine?”
—Isak Dinesen [Karen Blixen] (1885–1962)