TY  - JOUR
A1  - Brause, Rüdiger W.
A1  - Rippl, Michael
T1  - Noise suppressing sensor encoding and neural signal orthonormalization
N2  - In this paper we regard first the situation where parallel channels are disturbed by noise. With the goal of maximal information conservation we deduce the conditions for a transform which "immunizes" the channels against noise influence before the signals are used in later operations. It shows up that the signals have to be decorrelated and normalized by the filter which corresponds for the case of one channel to the classical result of Shannon. Additional simulations for image encoding and decoding show that this constitutes an efficient approach for noise suppression. Furthermore, by a corresponding objective function we deduce the stochastic and deterministic learning rules for a neural network that implements the data orthonormalization. In comparison with other already existing normalization networks our network shows approximately the same in the stochastic case but, by its generic deduction ensures the convergence and enables the use as independent building block in other contexts, e.g. whitening for independent component analysis. Keywords: information conservation, whitening filter, data orthonormalization network, image encoding, noise suppression.
KW  - information conservation
KW  - whitening filter
KW  - data orthonormalization network
KW  - image encoding
KW  - noise suppression
Y1  - 2010
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/7958
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30-79104
N1  - Postprint, zuerst in: IEEE Transactions on Neural Networks, Vol.9, No.4, pp.613-628, (1998)
ER  -