IEEE Trans Neural Netw Learn Syst. 2017 Jun;28(6):1360-1372. doi: 10.1109/TNNLS.2016.2536172. Epub 2016 Mar 28.
Many existing results on fault-tolerant algorithms focus on the single fault source situation, where a trained network is affected by one kind of weight failure. In fact, a trained network may be affected by multiple kinds of weight failure. This paper first studies how the open weight fault and the multiplicative weight noise degrade the performance of radial basis function (RBF) networks. Afterward, we define the objective function for training fault-tolerant RBF networks. Based on the objective function, we then develop two learning algorithms, one batch mode and one online mode. Besides, the convergent conditions of our online algorithm are investigated. Finally, we develop a formula to estimate the test set error of faulty networks trained from our approach. This formula helps us to optimize some tuning parameters, such as RBF width.
许多现有的容错算法研究结果都集中在单一故障源的情况，即训练好的网络受到一种类型的权值故障的影响。实际上，训练好的网络可能会受到多种类型的权值故障的影响。本文首先研究了开放权值故障和乘法权值噪声如何降低径向基函数（RBF）网络的性能。之后，我们定义了训练容错 RBF 网络的目标函数。基于该目标函数，我们开发了两种学习算法，一种是批量模式，另一种是在线模式。此外，我们还研究了在线算法的收敛条件。最后，我们提出了一种公式来估计我们的方法训练的有故障网络的测试集误差。该公式有助于我们优化一些调整参数，如 RBF 宽度。
