Restricted Boltzmann machine
A restricted Boltzmann machine, commonly abbreviated as RBM, is a neural network where neurons beyond the visible have probabilitistic outputs. The machine is restricted because connections are restricted to be from one layer to the next, that is, having no intra-layer connections.
As with contrastive Hebbian learning, there are two phases to the model, a positive phase, or wake phase, and a negative phase, or sleep phase.
During the positive phase, the output of the set of neurons is defined as follows:
This completes one wake-sleep cycle.
To update the weights, a wake-sleep cycle is completed, and weights updated as follows:
where η is some learning rate. In practice, several wake-sleep cycles can be run before doing the weight update. This is known as Gibbs sampling.
A batch update can also be used, where some number of patterns less than the full input set (a mini-batch) are uniformly randomly presented, the wake and sleep results recorded, and then the updates done as follows:
- Hinton, Geoffrey (August 2, 2010). "A practical guide to training restricted Boltzmann machines". University of Toronto Department of Computer Science.
- Cho, KyungHyun (March 14, 2011) "Improved Learning Algorithms for Restricted Boltzmann Machines". Aalto University.