资源列表
基于SOM的数据分类
- SOM神经网络也属于自组织型学习网络,只不过更特殊一点它属于自组织特征的映射网络。该网络是由一个全连接的神经元阵列组成的无教师,自组织,自学习的网络。(SOM neural network also belongs to self-organizing learning network, but more specifically, it belongs to self-organizing feature mapping network. The network is a non-teache
Chapter04
- 基于tensorflow 的神经网络的损失函数,学习率,正则化,滑动平均等方法(Method of loss function, learning rate, regularization and sliding average of neural network based on tensorflow)
Ch04
- 贝叶斯算法使用python ,内含测试数据文件,数据为多个txt格式的邮件文件。(The bayesian algorithm USES python, which contains test data files that are multiple mail files in TXT format.)
TransferEntropy1
- 传递熵算法代码,用于分析不同波动之间的关系,包括时延、权重等仅供参考(Transfer Entropy Algorithm Code, used to analyze the relationship between different fluctuations, including delay, weight, etc. for reference only)
yolo_tensorflow
- 基于YOLO的目标检测, 对十种物体进行识别和定位。(object detection based on YOLO, perform recognition and location to ten types of objects.)
sa_bp
- 基于模拟退火算法对BP神经网络进行的改进,有效提高了精度和迭代速度。(The improvement of BP neural network based on simulated annealing algorithm effectively improves the accuracy and speed of iteration.)
模拟退火算法
- 使用模拟退火算法对Bp神经网络进行改进,效果比较明显(Using simulated annealing algorithm to improve the Bp neural network, the effect is obvious.)
DNN
- 利用python3完整实现DNN,包括前向传播和反向传播。实现一个2次函数的拟合。(Complete implementation of DNN using python3, including forward propagation and reverse propagation. Implement a quadratic function fitting.)
SVM做图片处理
- 使用SVM算法对CIFAR-10图片数据集进行分类,包括模型的训练,测试和参数的调优(Using SVM algorithm to classify CIFAR-10 image data sets, including model training, testing and parameter tuning)
exercise_ZSL-master
- An exercise of zero-shot learning, including DAP, IAP, DeSIVE, SCoRe. By Chengzhe XU, Linyang HE, Yixu GAO
python_work
- 用tensorflow设计以三层的神经网络进行曲线拟合,采用梯度下降法。(Tensorflow is used to design three layers of neural network for curve fitting and gradient descent method.)
数据挖掘导论
- 《数据挖掘导论》经典电子书教程,课后习题答案,含丰富讲解。("Introduction to data mining" classic e-book tutorial, after-school exercise answers, rich explanation.)