Changeset 1054 for applications/bdmtoolbox/mex
- Timestamp:
- 06/07/10 17:25:57 (15 years ago)
- Location:
- applications/bdmtoolbox/mex/mex_classes
- Files:
-
- 3 modified
Legend:
- Unmodified
- Added
- Removed
-
applications/bdmtoolbox/mex/mex_classes/mexBM.m
r944 r1054 1 %> @file mexEpdf.m 2 %> @brief File mapping root class of BM from BDM 3 % ====================================================================== 4 %> @brief Abstract class of Bayesian Model (estimator), bdm::BM 5 % 6 %> This class provides a bridge between bdm::BM and Matlab 7 % ====================================================================== 1 8 classdef mexBM 2 9 properties 3 % description of internal variables10 %> description of internal variables of parameters 4 11 rv=RV 12 %> description of internal variables of data in condition 5 13 rvc=RV 14 %> description of internal variables of observed data 6 15 rvy=RV 7 % log of evidence (marginal likelihood) potentially computed by the16 %> log of evidence (marginal likelihood) potentially computed by the 8 17 % bayes rule for one step 9 18 log_evidence 10 % posterior density - offspring of mexEpdf!19 %> posterior density - offspring of mexEpdf! 11 20 apost_pdf 12 21 % … … 14 23 15 24 methods 25 %> check consistency of the object and fill defaults 16 26 function p=validate(p) 17 27 % checks if all paramateres match 18 28 end 29 %> dimensionality of the class: dims = [size_of_posterior size_of_data size_of_condition] 19 30 function dims=dimensions(p) 20 31 %please fill … … 22 33 dims = [0,0,0] % 23 34 end 35 %> Performs Bayesian update of the internal posterior using data \a dt and condition \a cond. 24 36 function obj=bayes(obj,dt,cond) 25 37 % transform old estimate into new estimate 26 38 end 39 %> Computes predictor of the observed data in the next step 27 40 function p=epredictor(obj,cond) 28 41 % return posterior density … … 39 52 r=obj.rvy; 40 53 end 54 %> Evidence of the last data, \f[f(y_t|y_0\ldots y_t-1, cond_0\ldots cond_t\f] 41 55 function ev = logevidence(obj) 42 56 ev = obj.log_evidence; 43 57 end 58 %> Posterior pdf 44 59 function post=posterior(obj); 45 60 post = obj.apost_pdf; -
applications/bdmtoolbox/mex/mex_classes/mexDirac.m
r983 r1054 1 %> @file mexDirec.m 2 %> @brief Matlab implementation of Dirac density 3 % ====================================================================== 4 %> @brief Unconditional Dirac density 5 % 6 %> \f[ f(x| x_i) = \delta(x-x_i)\f] 7 % ====================================================================== 1 8 classdef mexDirac < mexEpdf 2 9 % Dirac delta probability distribution -
applications/bdmtoolbox/mex/mex_classes/mexLaplace.m
r944 r1054 1 %> @file mexLaplace.m 2 %> @brief Matrlab implemnetation of Laplace density 3 % ====================================================================== 4 %> @brief Unconditional Laplace density 5 % 6 %> \f[ f(x|\mu,b) \propto \exp(-|x-\mu|/b)\f] 7 % ====================================================================== 1 8 classdef mexLaplace < mexEpdf 2 9 properties