25.10.2016 Views

SAP HANA Predictive Analysis Library (PAL)

sap_hana_predictive_analysis_library_pal_en

sap_hana_predictive_analysis_library_pal_en

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

3.1.6 Gaussian Mixture Model (GMM)<br />

GMM is a Gaussian mixture model in which each component has its own weight, mean, and covariance matrix.<br />

Weight means the importance of a Gaussian distribution in the GMM, and mean and covariance matrix are the<br />

basic parameters of a Gaussian distribution, as shown in the following formula:<br />

Expectation maximization (EM) algorithm is used to inference all of the unknown parameters of GMM. The<br />

algorithm performs two steps: the expectation step and the maximization step.<br />

The expectation step calculates the contribution of training sample i to the Gaussian k:<br />

The maximization step calculates the parameters weight, mean, and covariance matrix:<br />

GMM can be used in image segmentation, clustering, and so on. It gives the probability of a sample belonging<br />

to each Gaussian component.<br />

Prerequisite<br />

●<br />

No missing or null data in the inputs<br />

<strong>SAP</strong> <strong>HANA</strong> <strong>Predictive</strong> <strong>Analysis</strong> <strong>Library</strong> (<strong>PAL</strong>)<br />

<strong>PAL</strong> Functions P U B L I C 53

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!