搜索资源列表
networkalgorithm
- 神经网络源代码,及BP网络训练界面,其中的L-M算法非常实用-neural network source code, and BP training network interface, the L-M algorithm is very practical
基于C/C++环境下的模糊神经网络源程序
- 我这里有一个基于C/C++环境下的模糊神经网络源程序,用于训练神经网络并可更改样本实现你所需的功能,希望和大家一起分享-I have here on a C / C under the FNN source, used to train the neural network may vary sample implementation of the function you need, and hope to share with everyone
developfnn
- 这个程序是根据上一个上传的模糊神经网络的算法改进,更加精确,而且训练时间缩短。-this procedure is uploaded on a fuzzy neural network algorithm improvements, more precise, and reduce training time.
BP
- 训练好的BP神经网络 还有训练的数据 在C++控制台下的程序
对sinx在区间 内采样数点作为BP神经网络训练
- (1)对sinx在区间 内采样数点作为BP神经网络训练样本,然后利用该训练好的网络输出sinx的值。 (2)将函数换成 , ,重复(1)的实验。
BP
- bp神经网络程序,一个简单的训练算法和样本-bp neural network program, a simple algorithm and the training samples
BP-NN
- TC环境下,利用BP神经网络,通过输入输出数据对,训练网络,然后对同目标群体不同输入数据进行预测,并生存训练及预测结果文档。-It realized prediction with BP-NN.
Backprop_ANN_XOR
- 一个用C#开发的神经网络算法,例程中用神经网络算法验证了异或输出,并用图表绘制出了训练误差曲线-A C# developer neural network algorithm, neural network algorithm validation routines using the XOR output, and graphically plots the training error curve
neural_net
- 使用神经网络训练数据并且预测结果-The use of neural network training data and predict results. . . . .
CSharp_BP
- 一个C#编写的神经网络程序界面,适用于BP神经网络训练很好的例子。-The preparation of a C# neural network programming interface, suitable for training the BP neural network is a good example of.
License-Plate-Recognition
- 用C#实现车牌识别系统,采用了bp神经网络的训练方法-With C# license plate recognition system, using a neural network training methods bp
dssg
- 利用BP神经网络实现对柴油干点等多项指标的训练和预测.-The BP neural network
BP
- C#人工神经网络编程,实现神经网络的训练,测试和泛化-C# artificial neural network programming, neural network training, testing and generalization
ChinasenAnalyse20160821
- 该软件可以将中文语句分解为向量并保存,用于其他语言文字分析、统计或是神经网络训练。-The software can break down the Chinese statement into vectors and save them for other language analysis, statistics, or neural network training.
BPNETSerial
- 神经网络预测,训练输入数据是1620组9维数据,输出是1620组8维数据;测试输入数据为180组9维数据,输出是180组8维数据;训练后总误差为3.4%(The training input data are 1620 sets of 9 dimensional data, and the output is 1620 groups of 8 dimensional data; the test input data is 180 sets of 9 dimensional data and t