资源列表
BP
- bp神经网络,两个输入,一个输出。并且代入检测数据。获得神经网络预测值和检测值之间的差值,在时域上,将差值的变化值也一并获得。-bp neural network, two inputs and one output. And substituting the test data. Neural network prediction obtain a difference value and the detected values, in the time domain, the differe
gar_meter_ocr_exe_V3.0.1
- 图像识别,水表识别,燃气表识别,准确率99 以上,图片类型随意,图像大小随意,图像中字体支持多种,燃气表类型支持国内外主流类型。 http://blog.csdn.net/zhubenfulovepoem/article/details/51165887-Image recognition, identification meter, gas meter recognition accuracy rate above 99 , random image type, image size, r
11
- 基于弹性BP的数字手写体识别,利用弹性BP神经网络设计的数字手写识别算法。附录文档说明-BP neuralnetwork
the-dog
- 非洲野狗优化BP算法代码及结果具体算法案例-The African wild dog BP algorithm code and the specific case
GA-BP
- 神经网络遗传算法用于非线性函数的极值寻优matlab代码-Extreme Optimization matlab code of neural network genetic algorithm for nonlinear function
RBF
- 径向基神经网络应用实例,包括异或问题,RBF网络曲线拟合,GRNN网络曲线拟合,PNN网络用于坐标点分类-RBF neural networks used, including XOR problem, RBF network curve fitting, GRNN network curve fitting, PNN network to coordinate points classification
LFMfangzheng
- 在很多实际场合下,平稳性的假设往往不能成立,此时就需要引入非平稳信号或时变信号的分析与处理。所谓的时变是指信号的统计特性随时间变化。由于信号的这种性质,传统的傅立叶分析方法无法令人满意。对于时变信号,了解不同时刻附近的频域特征是至关重要的,因此,人们往往采用时间-频率联合描述的方法描述时变信号。-In many practical situations, stationarity assumptions often can not be established, then we need to
SFKF
- 强跟踪滤波器,可用于最优估计,用于故障诊断-strong kalman filtering
Ada_SVM
- AdaBoost 和SVM 组合 分类识别代码-combine AdaBoost and SVM to classification
PG_DEEP-master
- A fast learning algorithm for deep belief nets 文章代码-2006 A fast learning algorithm for deep belief nets
Sparse-Autoencoder
- 稀疏编码算法是一种无监督学习方法,它用来寻找一组“超完备”基向量来更高效地表示样本数据-2006 A fast learning algorithm for deep belief nets
GA-PSO-BPnn.pdf
- 基于GA-PSO-BP组合的神经网络应用研究,有需要请下载。-Application of Neural Network GA-PSO-BP portfolio based on the need to download.