Hi, a bug found in BNT regarding the strong root used in Junction tree engine for conditional linear Gaussian model. The last clique found in the elimination process is not guaranteed to be the strong root. Instead, a hybrid clique we called interface clique, that contains all discrete parents and at least one continuous node in a connected continuous component, is a guaranteed strong root for CLG model. We already theoretically proved this.

I would like to upload the function and change the code in BNT accordingly. Further, I would like to warn everybody who is using BNT Junction tree inference engine to be cautious with the results it returned.

@ wsun18: hi wsun18, Did u upload the file bcaz I am also getting the errors in junction tree. Please inform me. regards,

Usman Email: usmanstar2

Hi usmanstar2: I already uploaded the new version with bugs fixed (FullBNT-1.07). Also, I post message for BNT group members today. Enjoy!

Hi! I have a special question regading one specific application of Bayes inference and i would need one email of someone that could help me, or, otherwise, email me to josecamat@gmail.com. all the best!

Hi. I'm using the BNT toolbox for my thesis on dynamic bayesian networks. I'm still trying to get my head around it, but I think I've found some bugs in learn_params-dbn. I've fixed one of them, still trying to figure out the other.

Hi, I was wondering if there was actually any C code written for the BNT. In the "Why Matlab?" section, it says that C code currently is being written. If anyone has more information please email me at sumingchen@gmail.com

Hi, I'm a relative newbie with BNT, and I'm working on a problem in which the same decision is repeated in sequential periods, but only some of the chance nodes are observable (a POMDP with temporal structure). The functions for creating LIMIDs work well for capturing the decision aspect of the problem, but because my problem has a repetitive sequential structure and many time periods, I would prefer to code my network using dbn functions (ie inter/intra).

Can someone advise whether or not the dbn functions can handle decision nodes, and if so, what the syntax would me to make a dbn with decisions? Alternatively, is there a way to define a LIMID using inter/intra to denote repetitive structures?

The LIMID examples that are included with BNT don't illustrate the use of inter/intra, which suggests to me that these functions can't be used to generate LIMIDs, but I want to check with persons with more experience with BNT first before jumping to conclusions.

If anyone can offer advice, please feel free to email me at dmblum@gmail.com . Thanks!

Hi. I don'n know is there any version of this package or not? if anyone can help, email me please davood.barzegari@gmail.com

hi

help me ; help me plz I write code for Inference but it have error below:::

??? Error using ==> subsindex Function 'subsindex' is not defined for values of class 'cell'.

Error in ==> discrete_CPD.convert_to_table at 14 T = CPT(index{:});

Error in ==> discrete_CPD.convert_to_pot at 20

T = convert_to_table(CPD, domain, evidence);

Error in ==> jtree_inf_engine.enter_evidence at 57

pot{n} = convert_to_pot(bnet.CPD{e}, pot_type, fam(:), evidence);

Error in ==> Rafe_inference at 116 [engine,loglik] = enter_evidence(engine,evidence);

my code is :::::

clear all

clc

A?=xlsread('E:\DATA MINING\final_cut.xlsx');

N=6;

dag=zeros(N,N);

AS=1;AM=2;CC=3;SC=4;VT=5;DA=6;

dag(3:6,AS)=1;dag(2,3)=1;dag(3,4)=1;

discrete_nodes=1:N;

node_sizes=3 9 9 21 10?;

onodes=2:6;

bnet=mk_bnet(dag,node_sizes,'observed',onodes);

draw_graph(bnet.dag);

bnet.CPD{AS}=tabular_CPD(bnet,AS);

bnet.CPD{AM}=tabular_CPD(bnet,AM);

bnet.CPD{CC}=tabular_CPD(bnet,CC);

bnet.CPD{SC}=tabular_CPD(bnet,SC);

bnet.CPD{VT}=tabular_CPD(bnet,VT);

bnet.CPD{DA}=tabular_CPD(bnet,DA);

TrainingSamples?=cell(N,size(A,1));

for i = 1 : size(A,1)

TrainingSamples?(1,i)={A(i,1)'};

TrainingSamples?(2,i)={A(i,2)'};

TrainingSamples?(3,i)={A(i,3)'};

TrainingSamples?(4,i)={A(i,4)'};

TrainingSamples?(5,i)={A(i,5)'};

TrainingSamples?(6,i)={A(i,6)'};

bnet=learn_params(bnet,TrainingSamples?);

engine = jtree_inf_engine(bnet);

evidence = cell(1,N);

evidence{AM} = {A(i,2)'};

evidence{CC} = {A(i,3)'};

evidence{SC} = {A(i,4)'};

evidence{VT} = {A(i,5)'};

evidence{DA} = {A(i,6)'};

[engine,loglik] = enter_evidence(engine,evidence);

marg = marginal_nodes(engine, AS);

hi Email Address:::: rafe.torabi@gmail.com

help me ; help me plz I write code for Inference but it have error below:::

??? Error using ==> subsindex Function 'subsindex' is not defined for values of class 'cell'.

Error in ==> discrete_CPD.convert_to_table at 14 T = CPT(index{:});

Error in ==> discrete_CPD.convert_to_pot at 20

T = convert_to_table(CPD, domain, evidence);

Error in ==> jtree_inf_engine.enter_evidence at 57

pot{n} = convert_to_pot(bnet.CPD{e}, pot_type, fam(:), evidence);

Error in ==> Rafe_inference at 116 engine,loglik? = enter_evidence(engine,evidence);

my code is :::::

clear all

clc

A?=xlsread('E:\DATA MINING\final_cut.xlsx');

N=6;

dag=zeros(N,N);

AS=1;AM=2;CC=3;SC=4;VT=5;DA=6;

dag(3:6,AS)=1;dag(2,3)=1;dag(3,4)=1;

discrete_nodes=1:N;

node_sizes=3 9 9 21 10?;

onodes=2:6;

bnet=mk_bnet(dag,node_sizes,'observed',onodes);

draw_graph(bnet.dag);

bnet.CPD{AS}=tabular_CPD(bnet,AS);

bnet.CPD{AM}=tabular_CPD(bnet,AM);

bnet.CPD{CC}=tabular_CPD(bnet,CC);

bnet.CPD{SC}=tabular_CPD(bnet,SC);

bnet.CPD{VT}=tabular_CPD(bnet,VT);

bnet.CPD{DA}=tabular_CPD(bnet,DA);

TrainingSamples??=cell(N,size(A,1));

for i = 1 : size(A,1)

TrainingSamples??(1,i)={A(i,1)'}; TrainingSamples??(2,i)={A(i,2)'}; TrainingSamples??(3,i)={A(i,3)'}; TrainingSamples??(4,i)={A(i,4)'}; TrainingSamples??(5,i)={A(i,5)'}; TrainingSamples??(6,i)={A(i,6)'}; end

bnet=learn_params(bnet,TrainingSamples??);

engine = jtree_inf_engine(bnet);

evidence = cell(1,N);

evidence{AM} = {A(i,2)'};

evidence{CC} = {A(i,3)'};

evidence{SC} = {A(i,4)'};

evidence{VT} = {A(i,5)'};

evidence{DA} = {A(i,6)'};

engine,loglik? = enter_evidence(engine,evidence);

marg = marginal_nodes(engine, AS);