Mixture Density Mercer Kernels

Description

We present a method of generating Mercer Kernels from an ensemble of probabilistic mixture models, where each mixture model is generated from a Bayesian mixture density estimate. We show how to convert the ensemble estimates into a Mercer Kernel, describe the properties of this new kernel function, and give examples of the performance of this kernel on unsupervised clustering of synthetic data and also in the domain of unsupervised multispectral image understanding.

Resources

Name Format Description Link
33 Probabilistic_Kernels_2003.pdf https://c3.nasa.gov/dashlink/static/media/algorithm/Probabilistic_Kernels_2003.pdf
33 Virtual_Sensors-_Srivastava_2005.pdf https://c3.nasa.gov/dashlink/static/media/algorithm/Virtual_Sensors-_Srivastava_2005.pdf
33 Srivastava_ICML_2003.pdf https://c3.nasa.gov/dashlink/static/media/algorithm/Srivastava_ICML_2003.pdf

Tags

  • dashlink
  • nasa
  • ames

Topics

Categories