A learning procedure to identify weighted rules by neural networks
暂无分享,去创建一个
In many cases the identification of systems by means of fuzzy rules is given by taking these rules from a predetermined set of possible ones. In this case, the correct description of the system is to be given by a finite set of rules each with an associated weight which assesses its correctness or accuracy. Here we present a method to learn this consistence level or weight by a neural network. The design of this neural network as well as the features of the training models are discussed. The paper concludes with an example.
[1] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .
[2] Kurt Hornik,et al. FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .
[3] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.
[4] Vladik Kreinovich,et al. Arbitrary nonlinearity is sufficient to represent all functions by neural networks: A theorem , 1991, Neural Networks.