The Helmholtz machine is a name used by Geoff Hinton to describe a class of neural networks which learn the hidden structure of a set of data by being trained to create a generative model which can produce the original set of data. The hope is that by learning economical representations of the data, the underlying structure of the generative model should reasonably approximate the hidden structure of the data set. This is an unsupervised learning algorithm.
The networks are characterized by bottom-up and top-down (reentrant) connections between layers of stochastic elements. The wake-sleep algorithm is an unsupervised learning rule which has been suggested as a means to train the Helmholtz machine.
Helmholtz machines may also be used in applications requiring a supervised learning algorithm (e.g. character recognition, or position-invariant recognition of an object within a field).
Famous quotes containing the word machine:
“... in the fierce competition of modern society the only class left in the country possessing leisure is that of women supported in easy circumstances by husband or father, and it is to this class we must look for the maintenance of cultivated and refined tastes, for that value and pursuit of knowledge and of art for their own sakes which can alone save society from degenerating into a huge machine for making money, and gratifying the love of sensual luxury.”
—Mrs. H. O. Ward (1824–1899)