Misplaced Pages

Product of experts

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.
Machine learning technique

Product of experts (PoE) is a machine learning technique. It models a probability distribution by combining the output from several simpler distributions. It was proposed by Geoffrey Hinton in 1999, along with an algorithm for training the parameters of such a system.

The core idea is to combine several probability distributions ("experts") by multiplying their density functions—making the PoE classification similar to an "and" operation. This allows each expert to make decisions on the basis of a few dimensions without having to cover the full dimensionality of a problem: P ( y | { x k } ) = 1 Z ∏ j = 1 M f j ( y | { x k } ) {\displaystyle P(y|\{x_{k}\})={\frac {1}{Z}}\prod _{j=1}^{M}f_{j}(y|\{x_{k}\})}

where f j {\displaystyle f_{j}} are unnormalized expert densities and Z = ∫ d y ∏ j = 1 M f j ( y | { x k } ) {\displaystyle Z=\int {\mbox{d}}y\prod _{j=1}^{M}f_{j}(y|\{x_{k}\})} is a normalization constant (see partition function (statistical mechanics)).

This is related to (but quite different from) a mixture model, where several probability distributions p j ( y | { x j } ) {\displaystyle p_{j}(y|\{x_{j}\})} are combined via an "or" operation, which is a weighted sum of their density functions: P ( y | { x k } ) = ∑ j = 1 M α j p j ( y | { x k } ) , {\displaystyle P(y|\{x_{k}\})=\sum _{j=1}^{M}\alpha _{j}p_{j}(y|\{x_{k}\}),} with ∑ j α j = 1. {\displaystyle \sum _{j}\alpha _{j}=1.}

The experts may be understood as each being responsible for enforcing a constraint in a high-dimensional space. A data point is considered likely if and only if none of the experts say that the point violates a constraint.

To optimize it, he proposed the contrastive divergence minimization algorithm. This algorithm is most often used for learning restricted Boltzmann machines.

See also

References

  1. Hinton, G.E. (1999). "Products of experts". 9th International Conference on Artificial Neural Networks: ICANN '99. Vol. 1999. IEE. pp. 1–6. doi:10.1049/cp:19991075. ISBN 978-0-85296-721-8.
  2. Hinton, Geoffrey E. (2002-08-01). "Training Products of Experts by Minimizing Contrastive Divergence". Neural Computation. 14 (8): 1771–1800. doi:10.1162/089976602760128018. ISSN 0899-7667. PMID 12180402. S2CID 207596505.

External links


Stub icon

This computing article is a stub. You can help Misplaced Pages by expanding it.

Categories: