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:
“It’s so easy during those first few months to think that the problems will never end. You feel as if your son will never sleep through the night, will always spit up food after eating, and will never learn to smile—even though you don’t know any adults or even older children who still act this way.”
—Lawrence Kutner (20th century)
“We are all adult learners. Most of us have learned a good deal more out of school than in it. We have learned from our families, our work, our friends. We have learned from problems resolved and tasks achieved but also from mistakes confronted and illusions unmasked. . . . Some of what we have learned is trivial: some has changed our lives forever.”
—Laurent A. Daloz (20th century)
““What we know, is a point to what we do not know.” Open any recent journal of science, and weigh the problems suggested concerning Light, Heat, Electricity, Magnetism, Physiology, Geology, and judge whether the interest of natural science is likely to be soon exhausted.”
—Ralph Waldo Emerson (1803–1882)