泛函网络,functional network
1)functional network泛函网络
1.Construct theory of hierarchicalfunctional networks and its application in multiple numerical integral;层次泛函网络构造理论及其在多重数值积分中的应用
2.In this paper,by analyzing thefunctional network,a new model and learning algorithm of the serialfunctional networks is proposed.通过对泛函网络的分析,提出了一种序列泛函网络模型及学习算法,而网络的泛函参数利用梯度下降法来进行学习。
3.Functional network is a recently introduced extension of neural networks.泛函网络是最近提出的一种对神经网络的有效推广。
英文短句/例句
1.The Research to Forecasting Model and Algorithm Based on Functional Networks;基于泛函网络的预测模型及算法研究
2.Adaptive Functional Networks Loop Structures and Learning Algorithm自适应泛函网络循环结构与学习算法
3.Online Incremental Learning Algorithm and Application to Functional Networks泛函网络在线增量式学习算法及应用
4.Research on functional networks of flexible coordinate measuring machine modeling柔性坐标测量机建模的泛函网络研究
5.Numerical Integration Method Study Based on Function Network一种基于泛函网络求数值积分方法研究
6.The Application of Functional Equations in Artificial Neural Networks and Bio-Mathematics;泛函微分方程在神经网络及生物数学的应用
7.Qualitative Analysis of Functional Differential Systems and Its Applications in Neural Networks;泛函微分系统的定性分析及其在神经网络中的应用
8.Dynamics Analysis of Impulsive Functional Differential Systems and Their Application in Neural Networks;脉冲泛函微分系统的动力学分析及其在神经网络中的应用
9.On the Study of Asymptotic Behavior for Functional Differential Equations and Its Use for Static Neural Networks;泛函微分方程的渐近行为研究及其在神经网络中的应用
10.Improving the Accuracy of Density-Functional Theory Calculation for Absorption Energies: Neural Network and Genetic Algorithm提高密度泛函理论方法计算吸收能的精度：神经网络和遗传算法
11.Neural Networks Approach for New B3LYP Functional with Enlarged Training Set结合神经网络方法和扩大训练基组构建新B3LYP泛函
12.Robust stability of interval neural networks with mixed time-delays via augmented functional基于增广泛函的混合时滞区间神经网络的鲁棒稳定性
13.By means of suitable Lyapunov functionals, the exponential stability of periodic solutions for shunting inhibitory cellular neural networks( SICNNs) with delays and variable coefficients is studied.利用适当的李亚普若夫泛函,研究了时滞分流抑制型细胞神经网络的周期解的指数稳定性.
14.Blind Source Separation of Nonlinear Mixtures Based on Functional Link Artificial Neural Networks and Differential Evolution Algorithm基于泛函连接网络和差分进化算法的后非线性混叠信号盲分离方法
15.On the Energy Function of Chaotic Neural Networks with Trigonometric Function Self-feedback三角函数自反馈混沌神经网络能量函数研究
plex networks exist in nature and society widely.复杂网络广泛存在于自然界和社会中.
17.Study of Generalization Ability of Solar Irradiance Forecast on the Basis of Neural Network;太阳辐射预测神经网络泛化性能研究
18.Research of Flooding Attack and Prevention in Ad hoc Network;移动Ad hoc网络洪泛攻击与防范的研究
相关短句/例句
Functional networks泛函网络
1.Non-linear regression forecast model based on functional networks and learning algorithm;基于泛函网络的非线性回归预测模型及学习算法
2.Theory and learning algorithm of multi-dimensional functionapproximation based on functional networks;基于泛函网络的多维函数逼近理论及学习算法
3.Research on functional networks of flexible coordinate measuring machine modeling柔性坐标测量机建模的泛函网络研究
3)Function network泛函网络
1.In this paper, a kind of function networks with single input and single output and function network with double inputs and single output as basis functional network model is designed, and a new hierarchical functional network is presented.文中设计了一类单输入单输出泛函网络与双输入单输出泛函网络作为构造层次泛函网络基本模型,提出了一种层次泛函网络模型,给出了层次泛函网络构造方法和整体学习算法,而层次泛函网络的参数利用解方程组来进行逐层学习。
4)Fuzzy functional networkFuzzy泛函网络
5)Functional Link Artificial Neural Network泛函连接网络
1.Functional Link Artificial Neural Networks and agri-biodiversity analysis;泛函连接网络计算软件及其在生物多样性研究中的应用
6)neural network functional神经网络泛函数
延伸阅读
Марков过程的泛函Марков过程的泛函functional of a Markov processM仰助“过程的泛函【加犯份班司健a扮如d如vpr以犯岛;中y业，o.a月oT Map二招e.o np()朋eCea]一个以可测方式依赖于MaPKo.过程轨道的随机变量或随机函数，其可测性条件随具体情况而定.在MaP盆oB过程的一般理论中，采用以下的泛函定义.假设给定一个具有时间推移算子氏的非停止齐次M叩-Ko。过程(M田玉ov plx兀启弥)X二(xr，风，氏)，其相空间为可测空间(In纷s幽 blespaCe)LE，少)，设才是基本事件空间中包含每个形如{。:x，“B}(t)0，B任分)的事件的最小。代数，/’是对于所有可能的测度Px(x‘E)关于/’的完全化的交.如果对于每个t)O，7，关于。代数才门不是可测的，那么，称随机函数叭(‘)0)为Ma伴oB尽捍X的攀甲(丘功d沁n目of此MaJ改ov Pnx君邓)·人们特别关心的是M川阵..过程的乘性和加性泛函.它们分别润足条件下，十:，下;疏凡和，，十，，，，+氏大，s，亡》0.这里假定，，在【0，co)上是右连续的(代替这些条件，有时只假定对所有固定的s，t)O，这些条件关于P:几乎处处成立).在停止和非齐次过程的情形下，采用类似的方式来定义.MaPI..过程x‘(x，，心，不，P)的加性泛函的例子可以通过以下方式得到:设对于t<‘，，，等于f(x，)一f(x。)，或北f(气)d:，或随机函数f(x，)在:。10，，]中跳跃值的和，这里f(x)是有界并且关于岁可侧的函数(第二和第三个例子只在某些附加限制下有效).从任意加性泛函，.，可以得到乘性泛函以py，.在标准MaP-血过程的情况下，设t
