Leung Chi-Sing, Sum John Pui-Fai
Department of Electronic Engineering, the City Universityof Hong Kong, Kowloon Tong, Hong Kong.
IEEE Trans Neural Netw. 2008 Mar;19(3):493-507. doi: 10.1109/TNN.2007.912320.
In classical training methods for node open fault, we need to consider many potential faulty networks. When the multinode fault situation is considered, the space of potential faulty networks is very large. Hence, the objective function and the corresponding learning algorithm would be computationally complicated. This paper uses the Kullback-Leibler divergence to define an objective function for improving the fault tolerance of radial basis function (RBF) networks. With the assumption that there is a Gaussian distributed noise term in the output data, a regularizer in the objective function is identified. Finally, the corresponding learning algorithm is developed. In our approach, the objective function and the learning algorithm are computationally simple. Compared with some conventional approaches, including weight-decay-based regularizers, our approach has a better fault-tolerant ability. Besides, our empirical study shows that our approach can improve the generalization ability of a fault-free RBF network.
在针对节点开路故障的经典训练方法中，我们需要考虑许多潜在的故障网络。当考虑多节点故障情况时，潜在故障网络的空间非常大。因此，目标函数和相应的学习算法在计算上会很复杂。本文使用库尔贝克-莱布勒散度来定义一个目标函数，以提高径向基函数（RBF）网络的容错能力。假设输出数据中存在高斯分布的噪声项，确定了目标函数中的一个正则化项。最后，开发了相应的学习算法。在我们的方法中，目标函数和学习算法在计算上很简单。与一些传统方法（包括基于权重衰减的正则化项）相比，我们的方法具有更好的容错能力。此外，我们的实证研究表明，我们的方法可以提高无故障RBF网络的泛化能力。
