网络函数

Based on polynomial-interpolation and curve-fitting theory, this paper presents a special feed-forward neural network using Jacobi orthogonal polynomial activation-functions, which exploits a group of order-increased Jacobi orthogonal polynomial functions as the activation-function of hidden-layer neurons.

根据多项式插值与逼近理论，以一组零阀值特例 Jacobi 正交多项式（第二类 Chebyshev 正交多项式）作为隐层神经元的激励函数，构造一种基于 Jacobi 正交基的前向神经网络模型。

Based on the internal model of Jitterbug and its certain scheduling attributes with the quadratic cost function for a class of networked control system, we have derived the delay requirements of real-time closed loop control system and proceeded with analysis of delay compensation.

本文基于Jitterbug 内部模块特性，利用其特定的调度策略和性能指标函数，针对一类网络控制系统，导出了该实时闭环控制系统的性能优化时延需求，并进行了时延补偿分析。

Knap problem ; artificial neural network ; energy function ; combinatorial optimization

背包问题；神经网络；能量函数；组合优化

This adopts the optimization forward self-adaptive encoding based on Lagrangian cost function,to confi...

采用基于Lagrangian代价函数的最优前向自适应编码方法，根据网络带宽和缓冲区状态确定编码参数。

Heavy oil distillation column ; chaotic neural network ; Laguerre function ; predictive control ; adaptive control

重油分馏塔；混沌神经网络； Laguerre函数；预测控制；自适应控制

In order to solve the nonlinear problem of lampers, a pure-shear magneto-rtheological damper was designed. In view of its non-linear characteristics, it was proposed to make use of the radial basis function neural networks non-linear mapping capabilities and establish MR dampers inverse model to solve its problem of non-linear.

为了解决阻尼器的非线性问题，设计了一种纯剪切型磁流变阻尼器，并针对其非线性特性，提出了利用径向基函数神经网络的非线性映射能力，以建立磁流变阻尼器的逆模型。

The substitution model of RBF neural network was made respectively by 3 different test functions. The error analyses indicate that the fractional steps experiment design method is very practical for the substitution model needed large scale test sample points.

对3个测试函数建立RBF神经网络替代模型，其误差分析表明，分步试验设计方法对于需要大规模试验样本点的替代模型是非常实用的。

The determination of the best direction of step length vector and the adaptive adjustment of training rate for BP wavelet neural network are discussed.

讨论了BP小波神经网络在训练过程中减小误差函数时最优方向的确定和自适应调整学习率的方法。

To such a situation, this text has put forward and fitted the reliability problem of solving structure system of method of the state function of limit through the artificial neural network.

针对这样的情况，本文提出了通过人工神经网络拟合极限状态函数的方法来解决结构系统的可靠性问题。

The neural networks correction method combining the local map with radial based function networks and the global map with linear transform was applied to calculate the deformation resistance of the strip and the friction coefficient in the rolling deforming region.

采用径向基函数的局部映射和全局线性映射相结合的神经网络校正模型求解带钢变形抗力和轧制变形区的摩擦因数；并采用轧制变形区离散化方法分析轧制变形区内张力、摩擦力及金属变形抗力等在带钢轧制方向上的分布规律，从而建立轧制力在线计算数学模型。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。