摘要
论述了神经网络技术的原理、模型及其算法 ,并进一步指出了应用神经网络技术中的局限性和其相应的解决途径 .其中包括有数据的准备、模式的扩展、隐层数目的选择和计算过程中涉及的权值、步长、动量因子、压缩因子的处理 .
The principle, model and algorithm of neural network technique are discussed. The problems remaining to be solved in the application of the technique are pointed out, and they include preparation of data, expand of mode, determination of the number of hidden layer elements, and treatment of weight coefficients, step length, momentum factor and expressible factor in the process of computation. The application of neural network to lithologic identification being taken as an example, and the approaches of solving the problems are proposed.
出处
《西安石油学院学报（自然科学版）》
2002年第4期16-18,23,共4页
Journal of Xi'an Petroleum Institute（Natural Science Edition)
