Luttrell S P, April 2000, Invariance discovery by vector quantisation of noisy data, DERA technical report (Malvern, UK), DERA/S&P/SPI/TR000070
This report demonstrates how a vector quantiser for encoding noisy or distorted data, with the intention of eventually recovering the undistorted data, may be trained to produce results that are invariant with respect to the unwanted noise degrees of freedom. This is an example of self-organised invariance (or symmetry) discovery.