Show
Ignore:
Timestamp:
02/17/09 11:15:56 (16 years ago)
Author:
smidl
Message:

doc

Files:
1 modified

Legend:

Unmodified
Added
Removed
  • doc/html/classbdm_1_1MixEF.html

    r271 r275  
    8888<p> 
    8989An approximate estimation method for models with latent discrete variable, such as mixture models of the following kind: <p class="formulaDsp"> 
    90 <img class="formulaDsp" alt="\[ f(y_t|\psi_t, \Theta) = \sum_{i=1}^{n} w_i f(y_t|\psi_t, \theta_i) \]" src="form_66.png"> 
    91 <p> 
    92  where <img class="formulaInl" alt="$\psi$" src="form_67.png"> is a known function of past outputs, <img class="formulaInl" alt="$w=[w_1,\ldots,w_n]$" src="form_68.png"> are component weights, and component parameters <img class="formulaInl" alt="$\theta_i$" src="form_69.png"> are assumed to be mutually independent. <img class="formulaInl" alt="$\Theta$" src="form_70.png"> is an aggregation af all component parameters and weights, i.e. <img class="formulaInl" alt="$\Theta = [\theta_1,\ldots,\theta_n,w]$" src="form_71.png">.<p> 
     90<img class="formulaDsp" alt="\[ f(y_t|\psi_t, \Theta) = \sum_{i=1}^{n} w_i f(y_t|\psi_t, \theta_i) \]" src="form_12.png"> 
     91<p> 
     92 where <img class="formulaInl" alt="$\psi$" src="form_13.png"> is a known function of past outputs, <img class="formulaInl" alt="$w=[w_1,\ldots,w_n]$" src="form_14.png"> are component weights, and component parameters <img class="formulaInl" alt="$\theta_i$" src="form_15.png"> are assumed to be mutually independent. <img class="formulaInl" alt="$\Theta$" src="form_16.png"> is an aggregation af all component parameters and weights, i.e. <img class="formulaInl" alt="$\Theta = [\theta_1,\ldots,\theta_n,w]$" src="form_17.png">.<p> 
    9393The characteristic feature of this model is that if the exact values of the latent variable were known, estimation of the parameters can be handled by a single model. For example, for the case of mixture models, posterior density for each component parameters would be a BayesianModel from Exponential Family.<p> 
    9494This class uses EM-style type algorithms for estimation of its parameters. Under this simplification, the posterior density is a product of exponential family members, hence under EM-style approximate estimation this class itself belongs to the exponential family.<p> 
     
    132132<a class="el" href="classbdm_1_1emix.html">emix</a> *&nbsp;</td><td class="memItemRight" valign="bottom"><a class="el" href="classbdm_1_1MixEF.html#edc50e9640f049b846084748b18469a2">epredictor</a> () const </td></tr> 
    133133 
    134 <tr><td class="mdescLeft">&nbsp;</td><td class="mdescRight">Constructs a predictive density <img class="formulaInl" alt="$ f(d_{t+1} |d_{t}, \ldots d_{0}) $" src="form_112.png">. <br></td></tr> 
     134<tr><td class="mdescLeft">&nbsp;</td><td class="mdescRight">Constructs a predictive density <img class="formulaInl" alt="$ f(d_{t+1} |d_{t}, \ldots d_{0}) $" src="form_49.png">. <br></td></tr> 
    135135<tr><td class="memItemLeft" nowrap align="right" valign="top"><a class="anchor" name="f0dfb4375fef4e61c4cb062e5bac7c8c"></a><!-- doxytag: member="bdm::MixEF::flatten" ref="f0dfb4375fef4e61c4cb062e5bac7c8c" args="(const BMEF *M2)" --> 
    136136void&nbsp;</td><td class="memItemRight" valign="bottom"><a class="el" href="classbdm_1_1MixEF.html#f0dfb4375fef4e61c4cb062e5bac7c8c">flatten</a> (const <a class="el" href="classbdm_1_1BMEF.html">BMEF</a> *M2)</td></tr> 
     
    202202Array&lt; <a class="el" href="classbdm_1_1BMEF.html">BMEF</a> * &gt;&nbsp;</td><td class="memItemRight" valign="bottom"><a class="el" href="classbdm_1_1MixEF.html#90c21ab5a2af56d4b49e2eaef6eccc08">Coms</a></td></tr> 
    203203 
    204 <tr><td class="mdescLeft">&nbsp;</td><td class="mdescRight">Models for Components of <img class="formulaInl" alt="$\theta_i$" src="form_69.png">. <br></td></tr> 
     204<tr><td class="mdescLeft">&nbsp;</td><td class="mdescRight">Models for Components of <img class="formulaInl" alt="$\theta_i$" src="form_15.png">. <br></td></tr> 
    205205<tr><td class="memItemLeft" nowrap align="right" valign="top"><a class="anchor" name="e39faa70cebadc3296bd249040105e86"></a><!-- doxytag: member="bdm::MixEF::weights" ref="e39faa70cebadc3296bd249040105e86" args="" --> 
    206206<a class="el" href="classbdm_1_1multiBM.html">multiBM</a>&nbsp;</td><td class="memItemRight" valign="bottom"><a class="el" href="classbdm_1_1MixEF.html#e39faa70cebadc3296bd249040105e86">weights</a></td></tr> 
     
    334334<li><a class="el" href="mixef_8h-source.html">mixef.h</a><li>mixef.cpp</ul> 
    335335</div> 
    336 <hr size="1"><address style="text-align: right;"><small>Generated on Sun Feb 15 23:09:39 2009 for mixpp by&nbsp; 
     336<hr size="1"><address style="text-align: right;"><small>Generated on Mon Feb 16 10:06:35 2009 for mixpp by&nbsp; 
    337337<a href="http://www.doxygen.org/index.html"> 
    338338<img src="doxygen.png" alt="doxygen" align="middle" border="0"></a> 1.5.6 </small></address>