Function approximation capabilities of cloud reasoning neural networks
Shaowei Yu · Journal of Shandong University · 2010
A controlling model of an adaptive neuro-cloud inference system(ANCIS) was constructed by utilizing cloud theory with the function approximation property of the proved model.The Zadeh fuzzy inference neural nets were developed into cloud inference nets,and a model of ANCIS in Takagi-Sugeno type was established.The attribute functions and the inference rules of the system variables were devised with computational relations between the layers of input and output and a synthesized computational expression of system outputs ascertained.A successful proof of global approximation property of the model was accomplished by testifying that the computational expression of output results of the founded model satisfied the three hypothetic conditions of the Stone-Weirstrass theorem.