Computer Science – Neural and Evolutionary Computing
Scientific paper
2004-08-21
Computer Science
Neural and Evolutionary Computing
18 pages, 9 figures. Full version of a short paper that was published in the Digest of the 5th IMA International Conference on
Scientific paper
In this paper a stochastic generalisation of the standard Linde-Buzo-Gray (LBG) approach to vector quantiser (VQ) design is presented, in which the encoder is implemented as the sampling of a vector of code indices from a probability distribution derived from the input vector, and the decoder is implemented as a superposition of reconstruction vectors. This stochastic VQ (SVQ) is optimised using a minimum mean Euclidean reconstruction distortion criterion, as in the LBG case. Numerical simulations are used to demonstrate how this leads to self-organisation of the SVQ, where different stochastically sampled code indices become associated with different input subspaces.
No associations
LandOfFree
Using Stochastic Encoders to Discover Structure in Data does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Using Stochastic Encoders to Discover Structure in Data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Using Stochastic Encoders to Discover Structure in Data will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-383807