Aug 9, 2017
A Boltzmann machine is a network of symmetrically connected, neuron-like units that make stochastic decisions about whether to be on or off.
Stochastic decisions
Boltzmann machines have a simple learning algorithm (Hinton & Sejnowski, 1983)
The learning algorithm is very slow in networks with many layers of feature detectors
The learning algorithm is fast in "restricted Boltzmann machines".
Restricted Boltzmann machines have a single layer of feature detectors
Many hidden layers can be learned efficiently by composing restricted Boltzmann machines.
Boltzmann machines are used to solve two problems: search problems and learning problems.
