Based on expatiated the basic structure model and some general improved algorithms of BP neural network, this paper brings forward a new self-organization learning algorithm.
介绍了BP网络的基本结构模型与常见改进算法，在此基础上提出了一种新型的结构自组织BP网络算法。
In the arithmetic base, besides some general predict algorithm as glide average, exponential smoothness, linearity regress, etc, it adds BP neural network algorithm for forecast.
在算法库中，除了部分的常规预测算法，如滑动平均、指数平滑、线性回归等，还加入了BP神经网络算法进行预测。
General regression neural network is proved with certain superiority in the ability of approaching, classification and learning speed.
广义回归神经网络在逼近能力、分类能力和学习速度方面具有较强优势。
The simulation results show that the training time of Branched Feedforward Neural Network is obviously reduced and the classifying effect is much better as compared with general BP Network.
仿真结果表明，与一般BP网络相比较，分支前馈神经网络显著地减少了训练时间，且分类效果更好。
A practical developing software of neural network supporting many kinds of neural networks is designed. The software is general technical engineering people oriented and with graphic user interface.
设计了一种实用的面向普通工程技术人员，图形化用户界面，支持多种神经网络网型的神经网络开发软件。
It is found that it is better to predict the return rate with general regression neural network than with grey prediction and multiple regression model.
再以广义回归神经网络建立预测模型，与灰预测模型、多元回归模型进行预测能力及报酬率的比较分析。
Now, general prediction neural network has BP neural network and RBF neural network mainly.
目前常用的预测神经网络主要有BP神经网络和RBF神经网络。
Global asymptotic stability of general recurrent neural network models with S-type distributed delays on infinite intervals.
无限区间上s -分布时滞广义递归神经网络模型概周期解的全局渐近稳定性。
In this paper, we introduce a general-purpose Neural Network Simulating System.
本文介绍一个通用的神经网络模拟系统。
BP neural network model is based on the general test equipments, less test datas and not relevant to the engine's mathematical model.
BP神经网络模型依据的是普通试验设备、少量试验数据，与发动机的数学模型无关。
Then, We creatively make use of the nonlinear reflection ability and association learning ability of artificial neural network, and propose a general model of the stock market prediction.
然后运用神经网络模型的非线性映射能力和学习联想能力，提出了证券市场预测的通用模型。
A general forward displacement solution for parallel robot based on self-configuration quick BP neural network is presented, and analysis result for the engraving robot is given.
给出了基于自构型快速BP网络的并联机器人位置正解通用方法并以雕刻机器人为例进行了分析。
To improve the diversity of similar cases, similarity retrieval method based on partitioned clustering and General Fuzzy Min-Max neural network is developed.
为解决相似案例差异性问题，提出了基于划分聚类和模糊神经网络的设计案例相似性检索方法。
Based on the mathematic model of PMSM, a combination of an improved BP neural network and a general PID controller is used in its speed control system.
在分析永磁同步电机数学模型的基础上，采用改进型BP神经网络与传统PID控制相结合作为速度控制器，应用于永磁同步电机调速系统中。
A novel adaptive control method based neural network for a general class of MIMO non-affine nonlinear system was proposed, which are implicit function with respect to control input.
针对一类多输入多输出非仿射非线性系统，基于神经网络设计了一种自适应控制方案。
This paper predicts the chaotic signal based on a neural network. The experiment shows that the error of the result by using this method is less than that by using the general method.
针对混沌时间信号具有短期预测的特点，文章提出用神经网络构成的网络模型对混沌信号进行预测。
The paper, by adopting jointly Artificial Neural Network (ANN), general Amold mapping, and statistical methods, intends to formulate an algorithm based on image spatial domain watermark.
将人工神经网络（ANN）、广义猫映射及概率统计等知识相结合构造了一种图像空间域水印算法。
The paper, by adopting jointly Artificial Neural Network (ANN), general Amold mapping, and statistical methods, intends to formulate an algorithm based on image spatial domain watermark.
将人工神经网络（ANN）、广义猫映射及概率统计等知识相结合构造了一种图像空间域水印算法。
应用推荐