Problems
The Boltzmann machine would theoretically be a rather general computational medium. For instance, if trained on photographs, the machine would theoretically model the distribution of photographs, and could use that model to, for example, complete a partial photograph.
Unfortunately, there is a serious practical problem with the Boltzmann machine, namely that the learning seems to stop working correctly when the machine is scaled up to anything larger than a trivial machine. This is due to a number of effects, the most important of which are:
- the time the machine must be run in order to collect equilibrium statistics grows exponentially with the machine's size, and with the magnitude of the connection strengths
- connection strengths are more plastic when the units being connected have activation probabilities intermediate between zero and one, leading to a so-called variance trap. The net effect is that noise causes the connection strengths to random walk until the activities saturate.
Read more about this topic: Boltzmann Machine
Famous quotes containing the word problems:
“I am always glad to think that my education was, for the most part, informal, and had not the slightest reference to a future business career. It left me free and untrammeled to approach my business problems without the limiting influence of specific training.”
—Alice Foote MacDougall (1867–1945)
“The problems of all of humanity can only be solved by all of humanity.”
—Friedrich Dürrenmatt (1921–1990)
“If combat means living in a ditch, females have biological problems staying in a ditch for 30 days because they get infections.... Males are biologically driven to go out and hunt giraffes.”
—Newt Gingrich (b. 1943)