Neuron Model Utilizing Information of Local Samples for Forecasting Management State of Enterprise

In order to conquer the localization of the multi-layered feed forward neural networks, this paper presents a kind of neuron models utilizing information of local samples—the UILS neuron model, including an adaptive neuron model and a self-organization neuron model. Differing from traditional models, it fully employs the experience samples information within the local range and well embodies the association and analogy functions of cerebrum. Through investigating the properties of UILS and learning algorithm, we build a method based on the neuron model for forecasting the management state of enterprise according to the economic and technology indexes. It is verified that using the UILS model, expert experiences can be well expressed in the forecasting results.