基于优化步长和梯度法的置信规则库参数学习方法

置信规则库是传统规则库的推广.置信规则库中的参数由专家根据经验人为给定,削弱了置信规则库系统的仿真能力,因此,基于优化步长和梯度法设计了一种新的算法以实现规则库参数的自学习能力.采用该算法对一个已经建立的置信规则库参数进行了训练,训练结果表明新的算法具有收敛速度快、精度高等优点.

An Algorithm for Training Parameters in Belief Rule-bases Based on Gradient Methods with Optimization Step Size

Belief rule base is an extension of traditional rule base. The parameters in belief rule base are provided by experts subjectively, which weaken the simulation ability of the system. Based on the gradient methods with optimization step size, a new simple optimization algorithm is proposed to realize the self-learning capability of the rule base parameters, The algorithm has been applied to train parameters in an existing belief rule-base. The training results show that the new algorithm is simple, fast and effective.