Parity learning

Parity learning is a problem in machine learning. An algorithm that solves this problem must guess the function ƒ, given some samples (x, ƒ(x)) and the assurance that ƒ computes the parity of bits at some fixed locations. The samples are generated using some distribution over the input. The problem is easy to solve using Gaussian elimination provided that a sufficient number of samples (from a distribution which is not too skewed) are provided to the algorithm.

Noisy version ("Learning Parity with Noise")

In this version, the samples may contain some error. Instead of samples (x, ƒ(x)), the algorithm is provided with (x, y), where y = 1  ƒ(x) with some small probability. The noisy version of the parity learning problem is conjectured to be hard.

See also

References

This article is issued from Wikipedia - version of the 6/17/2015. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.