机器学习贝叶斯网络_机器学习中的贝叶斯网络

机器学习贝叶斯网络

贝叶斯网络 (Bayesian Network)

It also is known as a belief network also called student network which relies on a directed graph. It is defined for a rule for finding out the probability of an event given that another event already happened.

它也被称为信念网络，也称为学生网络，它依赖于有向图。 它定义了一个规则，用于在已知另一个事件已发生的情况下查找事件的可能性。

P (One event \ another event)

P(一个事件\另一个事件)

Here, we could isolate the probability of B given A and probability of A Given B and compute for simple probability. It is a very simple and important Bayes theorem problem for calculating the probability.

在这里，我们可以给隔离A和A由于B的概率计算简单的概率B的概率。 对于计算概率而言，这是一个非常简单且重要的贝叶斯定理问题。

Diagram:

图解：

	P(A/B) = P(B/A) * P(A) / P(B)
	P(B/A) = P(A/B) * P(B) / P(A)

贝叶斯网络 (Bayes Network)

A Bayes network is a structure that can be represented as a direct acyclic graph.

贝叶斯网络是可以表示为直接非循环图的结构。

1. It allows a compact representation of the distribution from the chain rule of Bayes network.

   它允许从贝叶斯网络的链规则中紧凑地表示分布。

2. It observes conditional independencies relationships between random variables.

   它观察随机变量之间的条件独立性关系。

A DAG (directed acyclic graph) is a finite directed graph with no directed cycles.

DAG(有向无环图)是没有有向环的有限有向图。

Diagram: Example of Bayes network

图：贝叶斯网络示例

There are 4 random variables in graph G, F, P, O:

图G ， F ， P ， O中有4个随机变量：

• In Genes (G) 0 is for bad and 1 is for good.

  在《 基因》(G)中， 0代表坏，1代表善。

• In bool (F) 0 is for no and 1 for yes.

  在布尔值(F)中， 0表示否，1表示是。

• We take grade in bad, okay and brilliant.

  我们的成绩不好，还不错，也很出色。

• Then we check performance in bad, okay and brilliant in the spot or no spot.

  然后，我们检查现场的表现是否良好，是否正常以及是否出色。

The edges in the graph encoded the dependencies in the graph,

图中的边编码了图中的依存关系，

• The "Genes" depends on the "good" and "bad and the form in bool "yes" and "no".

  “基因”取决于“好”和“坏”以及布尔型的形式“是”和“否”。

• The "Genes" in turn, determines whether the genes are "good" or "bad" with bool form in "yes" or "no".

  反过来，“基因”确定基因是“好”还是“坏”，且布尔形式为“是”或“否”。

The direction of arrows tells us about cause-effect relationships — "Performance" affects the "final probability" score.

箭头的方向告诉我们有关因果关系的信息-“性能”会影响“最终概率”得分。

Finally, let’s look at the tables associated with each of the nodes. Formally, these are called conditional probability distributions (CPDs).

最后，让我们看一下与每个节点关联的表。 在形式上，这些被称为条件概率分布(CPD)。

Conditional probability "P":

条件概率“ P”：

The CPDs for "Genes" and "form" are simple, because these variables do not depend on any of the other variables. Basically, the table encodes the probabilities of these variables. As you might have noticed, the values in each of the tables must sum to 1.

“基因”和“形式”的CPD很简单，因为这些变量不依赖于任何其他变量。 基本上，该表对这些变量的概率进行编码。 您可能已经注意到，每个表中的值总和必须为1。

The CPD for "O" encodes the conditional probabilities p(prob=O | conditional prob. = P).

“ O”的CPD编码条件概率p(prob = O |条件概率= P)。

The CPD for "P" is easy to understand because it has two parents, the conditional probabilities will be of the form(prob. P | Genes=G, form = F), that is, what is the probability of "prob." being P. Each row now corresponds to a pair of values of "Genes" and "form." Again, the row values add up to 1. An essential requirement for Bayesian networks is that the graph must be a directed acyclic graph (DAG).

“ P”的CPD很容易理解，因为它有两个亲代，条件概率的形式为(概率P |基因= G，形式= F)，即“概率”的概率是多少。 现在为P。每一行对应于一对“ Genes”和“ form”值。 同样，行值加起来为1。贝叶斯网络的基本要求是该图必须是有向无环图(DAG)。

Probability "O":

概率“ O”：

Working:

加工：

• Each node in the Bayes network will have a CPD associated with it.

  贝叶斯网络中的每个节点都将具有与其关联的CPD。

• If the node has parents, the associated CPD represents P(value \ Parents value).

  如果节点具有父级，则关联的CPD表示P(值\父级值)。

• If a node has no parents, the CPD represents P(value), the unconditional probability of the value.

  如果节点没有父节点，则CPD表示P(值)，即该值的无条件概率。

Conclusion: In this article, we have learned about Bayesian network and Bayes network with example and conditional probability distribution. We will know more about ML in the upcoming article. Have a nice day! Happy learning!

结论：在本文中，我们通过示例和条件概率分布了解了贝叶斯网络和贝叶斯网络 。 在接下来的文章中，我们将更多地了解ML。 祝你今天愉快！ 学习愉快！

翻译自: https://www.includehelp.com/ml-ai/bayesian-network-in-machine-learning.aspx

机器学习贝叶斯网络