Application of Unascertained Neural Networks to Financial Early Warning

摘要

Artificial neural network (ANN) has outstanding characteristics in machine learning, fault, tolerant, parallel reasoning and processing nonlinear problem abilities. Unascertained system that imitates the human brain's thinking logical is a kind of mathematical tools used to deal with imprecise and uncertain knowledge. Integrating unascertained method with neural network technology, the reasoning process of network coding can be tracked, and the output of the network can be given a physical explanation. A unascertained neural network was set up. It can be compared with the fuzzy network, so that their own advantages and shortcomings can be found and further study can be made on the uncertainty network to improve the uncertainty network more complete.