1)  Linear programming neural network

2)  Neural network path planning

3)  Linear neural network

1.
Application of linear neural network in calibration of accelerometer;

2.
A Cointegration Analysis Based on Linear Neural Network;

3.
In this paper linear neural network was applied to adaptive noise cancellation technology,and the neural network was trained by least mean square (LMS) algorithm.

4)  linear neural networks

1.
This method used genetic algorithm optima linear neural networks firstly, then fitting the output of sensor consistency, also putting up a stopping-genetic evolution and adapting-variation methods.

2.
Firstly the basic principles of linear neural networks and Fourier transform are introduced;meanwhile computational method of linear neural network weights is given;secondly the steps of periodic signals decompositions is given on the basis of linear neural networks.

5)  nonlinear neural network

1.
A controlling model of the proposed system is then put forward based on nonlinear neural networks,with a neural identifier and a controller being also designed.

6)  linear artificial neural network

1.
According to the relationship between precipitation and discharge of groundwater,a model of linear artificial neural network is set and used for dynamic prediction of discharge of groundwater.

2.
Based on the time series, a model of linear artificial neural network is set and used for dynamic prediction of discharge of groundwater.

 非线性规划nonlinear programming    目标函数是非线性函数或约束条件不全是线性等式（不等式）的一类数学规划。在科学管理和其他领域中，很多实际问题可以归结为线性规划，但还有另一些问题属于非线性规划。由于非线性规划含有深刻的背景和丰富的内容，已发展为运筹学的重要分支，并且在最优设计、管理科学、系统控制等领域得到越来越广泛的应用。   非线性规划的研究始于1939年，是由W.卡鲁什首次进行的，40年代后期进入系统研究，1951年H.W.库恩和A.W.塔克尔提出最优化的判别条件，从而奠定了非线性规划的理论基础，后来在理论研究和实用算法方面都有很大的发展。   非线性规划求解方法可分为无约束问题和约束问题来讨论，前者实际上就是多元函数的极值问题，是后一问题的基础。无约束问题的求解方法有最速下降法、共轭梯度法、变尺度法和鲍威尔直接法等。关于约束问题情况比较复杂，因为在迭代过程中除了要使目标函数下降外，还要考虑近似解的可行性。总的原则是设法将约束问题化为无约束问题；把非线性问题化为线性问题从而使复杂问题简单化。求解方法有可行方向法、制约函数法、简约梯度法、约束变尺度法、二次规划法和约束集法等。虽然这些方法都有较好的效果，但是尚未找到可以用于解决所有非线性规划的统一算法。