Equilibrium State
The network is run by repeatedly choosing a unit and setting its state according to the above formula. After running for long enough at a certain temperature, the probability of a global state of the network will depend only upon that global state's energy, according to a Boltzmann distribution. This means that log-probabilities of global states become linear in their energies. This relationship is true when the machine is "at thermal equilibrium", meaning that the probability distribution of global states has converged. If we start running the network from a high temperature, and gradually decrease it until we reach a thermal equilibrium at a low temperature, we may converge to a distribution where the energy level fluctuates around the global minimum. This process is called simulated annealing.
If we want to train the network so that the chance it will converge to a global state is according to an external distribution that we have over these states, we need to set the weights so that the global states with the highest probabilities will get the lowest energies. This is done by the following training procedure.
Read more about this topic: Boltzmann Machine
Famous quotes containing the words equilibrium and/or state:
“There is a relation between the hours of our life and the centuries of time. As the air I breathe is drawn from the great repositories of nature, as the light on my book is yielded by a star a hundred millions of miles distant, as the poise of my body depends on the equilibrium of centrifugal and centripetal forces, so the hours should be instructed by the ages and the ages explained by the hours.”
—Ralph Waldo Emerson (1803–1882)
“Wisdom has lost repute because it so often applies to a state of affairs that no longer exists.”
—Mason Cooley (b. 1927)