Lines Matching full:mixture
50 function is assumed to be a Gaussian mixture, one component per class. Using the training data the
303 density function in the form of a Gaussian mixture distribution with a specified number of mixtures.
306 space drawn from a Gaussian mixture:
313 \f$a_k\f$ and covariance matrix \f$S_k\f$, \f$\pi_k\f$ is the weight of the k-th mixture. Given the
315 likelihood estimates (MLE) of all the mixture parameters, that is, \f$a_k\f$, \f$S_k\f$ and
324 the formula below) of sample i to belong to mixture k using the currently available mixture
329 At the second step (Maximization step or M-step), the mixture parameter estimates are refined using
343 matrix and \f$\mu_k\f$ is a mixture-dependent "scale" parameter. So, a robust computation scheme
352 Estimation for Gaussian Mixture and Hidden Markov Models_. Technical Report TR-97-021,
