自动制图综合人工神经元网络方法的研究

现代神经生理学研究表明 ,人脑的大量神经元构成有所分工而又紧密联系的神经元网络 ,它的结构和功能可以采用物理可实现的系统人工神经元网络来模拟。制图综合是人脑神经元网络获取、处理、输出地理信息的复杂视觉思维过程 ,可以用人工神经元网络来模拟。文中探讨了制图综合的人工神经元网络的设计 ,并对用于实现自动制图综合的结果进行分析 ,指出其应用前景。

The Research on Neural Network Methods for Automated Generalization

It is proved by investigation of modern neural physiology that enormous nets in human's brain make up networks. The net has it's own tasks but keep in contact with each other. The structure and function of the network can be imitated by neural networks. Map generalization is a complicated thinking process which deals with geographic information that can also be imitated by neural networks. The design of neural networks for cartographic generalization is studied in this paper and the experiment results which apply the methods in map generalization are analyzed. It inaugurates a new way in automated map generalization.