BayesServer:InvalidNetworkException:节点[知识]的分配为空 [英] BayesServer: InvalidNetworkException: Node [Knowledge] has a null distribution

问题描述

我正在尝试使用 BayesServer库建立动态贝叶斯网络.我有以下实现网络的方法

I am trying to build a Dynamic Bayesian Network using the BayesServer library in C# for my Unity3D game. I have the following method which implements the network

// numberOfDistractors and levelId will be used later for added complexity in modeling
void InitializeNetworkForLevel(int numberOfDistractors, int levelId)
{
    beliefNet = new BayesServer.Network();

    // add a knowledge node which is a latent variable (parameter to be learned from observed values
    KTrue = new State("KTrue");
    KFalse = new State("KFalse");
    knowledge = new Variable("Knowledge", KTrue, KFalse);
    knowledgeNode = new Node(knowledge)
    {
        TemporalType = TemporalType.Temporal // this is a time series node, hence re-used for each time slice
    };
    beliefNet.Nodes.Add(knowledgeNode);

    // add a question node, which denotes the oberved variable whether the question is answered correctly or not
    // this node has two states, namely correct or incorrect
    QTrue = new State("QTrue");
    QFalse = new State("QFalse");
    question = new Variable("Question", QTrue, QFalse);
    questionNode = new Node(question)
    {
        TemporalType = TemporalType.Temporal  // this is a time series node, hence re-used for each time slice
    };
    beliefNet.Nodes.Add(questionNode);

    // add a link from knowledge node to question node
    beliefNet.Links.Add(new Link(knowledgeNode, questionNode, 0));
    for (int i = 1; i <= 5; i++) 
        beliefNet.Links.Add(new Link(knowledgeNode, knowledgeNode, i)); // time series link (order/lag i)
    QueryNetwork(true);
}

然后是另一种推断方法:

and then another method for making inference:

void QueryNetwork(bool isAnswerCOrrect)
{

    StateContext kTrueTime0 = new StateContext(KTrue, 0);
    StateContext kFalseTime0 = new StateContext(KFalse, 0);

    Table priorKnowledge = knowledgeNode.NewDistribution(0).Table;
    priorKnowledge[kTrueTime0] = 0.5;
    priorKnowledge[kFalseTime0] = 0.5;
    // NewDistribution does not assign the new distribution, so it still must be assigned
    knowledgeNode.Distribution = priorKnowledge;

    // the second is specified for time >= 1
    Table learnRate = knowledgeNode.NewDistribution(1).Table;
    // when specifying temporal distributions, variables which belong to temporal nodes must have times associated
    // NOTE: Each time is specified relative to the current point in time which is defined as zero, 
    // therefore the time for variables at the previous time step is -1
    StateContext kTrueTime1 = new StateContext(KTrue, -1);
    StateContext kFalseTime1 = new StateContext(KFalse, -1);
    learnRate[kTrueTime1, kTrueTime0] = 0.5;
    learnRate[kFalseTime1, kTrueTime0] = 0.5;
    learnRate[kTrueTime1, kFalseTime0] = 0.5;
    learnRate[kFalseTime1, kFalseTime0] = 0.5;
    knowledgeNode.Distributions[1] = learnRate;

    Table answerStatus = questionNode.NewDistribution().Table;
    StateContext qTrue = new StateContext(QTrue, 0);
    StateContext qFalse = new StateContext(QFalse, 0);
    answerStatus[qTrue, kTrueTime0] = 0.5;
    answerStatus[qFalse, kTrueTime0] = 0.5;
    answerStatus[qTrue, kFalseTime0] = 0.5;
    answerStatus[qFalse, kFalseTime0] = 0.5;
    questionNode.Distribution = answerStatus;

    // optional check to validate network
    beliefNet.Validate(new ValidationOptions());
    // at this point the network has been fully specified

    // we will now perform some queries on the network
    RelevanceTreeInference inference = new RelevanceTreeInference(beliefNet);
    RelevanceTreeQueryOptions queryOptions = new RelevanceTreeQueryOptions();
    RelevanceTreeQueryOutput queryOutput = new RelevanceTreeQueryOutput();

    // set some temporal evidence
    if (isAnswerCOrrect)
        inference.Evidence.Set(question, new double?[] { 1, 0 }, 0, 0, 2);
    else
        inference.Evidence.Set(question, new double?[] { 0, 1 }, 0, 0, 2);

    queryOptions.LogLikelihood = true; // only ask for this if you really need it
    inference.Query(queryOptions, queryOutput); // note that this can raise an exception (see help for details)

    Debug.Log("LogLikelihood: " + queryOutput.LogLikelihood.Value);
}

但是，当尝试使用QueryNetwork方法验证网络时，出现以下异常:

However, I am getting the following exception when trying to validate the network in QueryNetwork method:

InvalidNetworkException:节点[知识]的分配为空.

InvalidNetworkException: Node [Knowledge] has a null distribution.

BayesServer.Network.Validate(BayesServer.ValidationOptions选项) (在:0处)

BayesServer.Network.Validate (BayesServer.ValidationOptions options) (at :0)

BayesNet.QueryNetwork(System.Boolean isAnswerCOrrect)(在 资产/脚本/BayesNet.cs:97)

BayesNet.QueryNetwork (System.Boolean isAnswerCOrrect) (at Assets/Scripts/BayesNet.cs:97)

BayesNet.InitializeNetworkForLevel(System.Int32 numberOfDistractors， System.Int32 levelId)(位于Assets/Scripts/BayesNet.cs:59)

BayesNet.InitializeNetworkForLevel (System.Int32 numberOfDistractors, System.Int32 levelId) (at Assets/Scripts/BayesNet.cs:59)

BayesNet.Start()(位于Assets/Scripts/BayesNet.cs:21)

BayesNet.Start () (at Assets/Scripts/BayesNet.cs:21)

当我已经在QueryNetwork方法中指定知识节点时，为什么它说知识节点具有空分布.尽管我可以使用以下代码来解决此问题:

Why does it say that Knowledge Node has null distribution when I am already specifying it in the QueryNetwork method. Although I am able to fix this using the following piece of code:

ValidationOptions opt = new ValidationOptions();
opt.AllowNullDistributions = true;
// optional check to validate network
beliefNet.Validate(opt);

此外，我假设第一级的所有概率为50％，如何根据第一级的推论来更改第二级的这些值?

Further, I have assumed all the probabilities to be 50% for the first level, how would I change these values for the second level on the basis of inference from the first level?

最终，我想构建如下图所示的网络，其中每个级别的Distractors数量都是不同的(如果过于复杂则可能是相同的):

Eventually, I'd like to build something like the network shown in image below where the number of Distractors is different on every level (or may be same if it is too complex):

推荐答案

当我怀疑您在潜在节点上只需要滞后1时，您似乎在添加滞后1至5.尽管推理不是必需的，但为了进行测试，我建议在用户界面中展开网络以检查DBN是否符合您的期望.请注意，仅添加滞后1不会限制时间步长，只是每个步长仅连接到前一个时间步长.

It looks like you are adding lags 1 through 5, when I suspect you only need lag 1 on the latent node. Although not required for inference, to test this I would suggest unrolling the network in the User Interface to check that the DBN is as you expect. Note that only adding lag 1 does not restrict the number of time steps, just that each step is only connected to the previous time step.

这篇关于BayesServer:InvalidNetworkException:节点[知识]的分配为空的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！