针对BP算法收敛速度慢的特点，在隐含层上加入了关联节点，改善了网络的学习速率和适应能力。
Aiming at the slow convergence rate of BP neural network, append a correlative node on hidden layer, improve the adaptive ability and rate of studying of neural network.
基于输出层函数为线性函数的三层前馈神经网络，结合自适应步长和动量解耦的伪牛顿算法及迭代最小二乘法导出了一种混合算法。
On the basis of both adaptive BP algorithm and Newtons method, Quasi Newton algorithm with adaptive decoupled step and momentum (QNADSM) for feed-forward neural networks is derived.
该方法采用一个三层BP网络辩识交流调速系统的特性，用另一个CMAC神经网络作为自适应控制器。
By using BP neural networks to oltain the model of AC speed adjustable system; another CMAC is used for adaptive controller.
自适应小波神经网络检测法就是利用小波函数取代通常神经网络中隐层的作用函数来实现的。
Adaptive wavelet neural network intelligent detection is a method in which the wavelet function substitutes for the activation function of hidden layer in the neural network.
继而研究了模糊artmap网络用于特征层融合识别的方法，并提出了一种网络警戒参数自适应调整新算法。
Next the general method of applying fuzzy ARTMAP model to feature level fusion is also expounded and we put forward a learning algorithm with adaptive vigilance parameters for each cluster.
提出了一种隐层结构自适应学习的径向基函数网络(HSARBF)水声目标分类器。
This paper proposes a hidden layer structure adaptive radial basis function (HSARBF) classifier.
其目的是通过本课题的研究，进一步提高无线自组网的动态自适应能力，完善其网络层提供的路由服务，并通过不同协议之间的分析和对比，寻找最优的性能。
And developed a routing protocol based on this infrastructure. The purpose is to improve the dynamic adaptability, the routing service and to find the best performance by the research.
利用人工神经网络法中的自适应共振理论优选钻头 ，将定性、定量优选因素作为输入层神经元 ，形成一种综合性选型方法 。
The new network model is formed by incorporating the two concepts of fuzzy set theory, closeness and closest principles, with adaptive resonance theory (ART).
FCHT利用这些信息计算出触发切换的自适应阀值，通过跨层设计方法使网络层和应用层的切换相衔接。
FCHT compute the self-adapt trigger value using the information. We join the handovers in application layer and in network layer closely by cross-layer method also.
该算法在无线传感器网络MAC层实现了网络规模的可扩展性，增强了网络自适应网络规模变化的能力。
This algorithm implemented the expansibility of network size in MAC layer, and enhanced the adaptive ability of network to the variety of the network size.
该算法在无线传感器网络MAC层实现了网络规模的可扩展性，增强了网络自适应网络规模变化的能力。
This algorithm implemented the expansibility of network size in MAC layer, and enhanced the adaptive ability of network to the variety of the network size.
应用推荐