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:
“If we fail to meet our problems here, no one else in the world will do so. If we fail, the heart goes out of progressives throughout the world.”
—Eleanor Roosevelt (1884–1962)
“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)
“In many ways, life becomes simpler [for young adults]. . . . We are expected to solve only a finite number of problems within a limited range of possible solutions. . . . It’s a mental vacation compared with figuring out who we are, what we believe, what we’re going to do with our talents, how we’re going to solve the social problems of the globe . . .and what the perfect way to raise our children will be.”
—Roger Gould (20th century)