Ideal reformulation of belief networks
Ideal reformulation of belief networks
复制标题
信念网络的理想重构
DOI：
--
复制
发表时间：
1990
期刊：
影响因子：
--
通讯作者：
E. Horvitz
中科院分区：
文献类型：
--
作者：
J. Breese;E. Horvitz
信念网络的智能重构可以大大提高推理的效率。然而，重构所花费的时间不可用于执行推理。因此，在时间压力下，需要在用于重新制定网络的时间和用于实施解决方案的时间之间进行权衡。我们调查这一分区的资源转化为时间适用于重新制定和时间用于推理。我们将首先描述计算不确定性下资源的理想划分的一般原理。这些原则适用于各种各样的问题，这些问题可以分为解决问题的相互依赖的阶段。之后，我们将介绍我们的实证研究的结果，确定理想的时间量，致力于寻找集群的信念网络的问题。在这项工作中，我们获得并利用概率分布来表征（1）将网络实例重新表示为一组集团的替代启发式搜索方法的性能，以及（2）在各种信念网络上执行推理过程的时间。给定一个偏好模型，该模型描述了作为其计算所需延迟的函数的解决方案的值，系统选择一个理想的时间致力于重新制定。这项工作得到了罗克韦尔国际科学中心和美国国家科学基金会的资助，资助号为IRI-8703710。
The intelligent reformulation or restructuring of a belief network can greatly increase the efficiency of inference. However, time expended for reformulation is not available for performing inference. Thus, under time pressure, there is a tradeoff between the time dedicated to reformulating the network and the time applied to the implementation of a solution. We investigate this partition of resources into time applied to reformulation and time used for inference. We shall describe first general principles for computing the ideal partition of resources under uncertainty. These principles have applicability to a wide variety of problems that can be divided into interdependent phases of problem solving. After, we shall present results of our empirical study of the problem of determining the ideal amount of time to devote to searching for clusters in belief networks. In this work, we acquired and made use of probability distributions that characterize (1) the performance of alternative heuristic search methods for reformulating a network instance into a set of cliques, and (2) the time for executing inference procedures on various belief networks. Given a preference model describing the value of a solution as a function of the delay required for its computation, the system selects an ideal time to devote to reformulation. ∗This work was supported by Rockwell International Science Center and the National Science Foundation under Grant IRI-8703710.