Annealing Robust Fuzzy Neural Networks for Modeling of Molecular Autoregulatory Feedback Loop Systems

In this paper, the annealing robust fuzzy neural networks (ARFNNs) are proposed to improve the problems of fuzzy neural networks for modeling of the molecular autoregulatory feedback loop systems with outliers. Firstly, the support vector regression (SVR) approach is proposed to determine the initial structure of the ARFNNs. Because of a SVR approach is equivalent to solving a linear constrained quadratic programming problem under a fixed structure of SVR, the number of hidden nodes, the initial parameters and the initial weights of the ARFNNs are easy obtained via the SVR approach. Moreover, the results of the SVR are used as initial structure in the ARFNNs. At the same time, an annealing robust learning algorithm (ARLA) is used as the learning algorithm for the ARFNNs, and applied to adjust the parameters in the membership function as well as weights of the ARFNNs. That is, an ARLA is proposed to overcome the problems of initialization and the cut-off points in the robust learning algorithm. Hence, when an initial structure of the ARFNNs are determined by a SVR approach, the ARFNNs with the ARLA have fast convergence speed and robust against outliers for the modeling of the molecular autoregulatory feedback loop systems.