搜索资源列表
ellipse.m
- Simulation/visual plots of an ellipsoid dataset applied to an SVM having three kernel functions i.e. radial basis, quadratic and cubic kernel functions.
belajar_decision_tree
- Decision Tree Classifier applied on standard Iris dataset using Python.
19931107_135603_starea17
- IPIX雷达1993年采集的一组数据,数据编号17,为驻留数据-A dataset collected by IPIX RADAR at starea mode in 1993.
Cart-tree
- 实现CART树回归,树的生成与剪枝过程,并与简单线性回归进行对比-Implement a regression tree generation algorithm when the leaf nodes indicate 3rd order polynomials. Test your program with the dataset and compare the results with those of simple linear regression
NN-Back-Propagation-Generalized
- Solving XOR-problem and consecutively try MNIST-dataset with fundamental level of understanding on neural networks. Recommendable for beginners ( As I am :) ) And it s fully documented.
LogisticRegression
- Logistic Regression on IRIS Dataset using TensorFlow
eps_operator
- 对数据进行边界保护平滑处理,可以选择平滑窗口大小-Apply Edge-preserve Smoothing (EPS) operation on input dataset with selected window size
Using-Data-from-MOLA-
- 使用MOLA的数据 火星轨道仪激光高度计(MOLA),NASA火星上的仪器 1998年和1999年收集了2700万次高程测量。 在这里,我们工作一个中等分辨率的数据集-Using Data MOLA The Mars Orbiter Laser Altimeter (MOLA), an instrument aboard NASA s Mars Global Surveyor, collected 27 million elevation measurements
knn_logistic_naiveBayes
- 统计机器学习经典分类算法MATLAB代码,付数据集。包括knn算法,逻辑斯蒂回归和朴素贝叶斯算法。-Classical statistical machine learning classification algorithm MATLAB code, pay dataset. Including knn algorithm, logistic regression and naive Bayes algorithm.
Class_3_Code
- 将concrete_data.mat文件导入到MATLAB中,其中attributes为影响混凝土抗压强度的7个输入变量,strength为混凝土的抗压强度,即输出变量; 将整个数据集中的103个样本随机划分为训练集与测试集,其中训练集包含80个样本,测试集包含23个样本; 将训练集与测试集数据进行归一化; 建立BP神经网络,并训练; 利用训练好的BP神经网络对测试集中的23个样本的抗压强度进行预测; 输出结果并绘图(真实值与预测值对比图)(The concrete_data.mat
googlenet_places205.tar
- 是GoogLeNet在placesCNN205数据集里迭代模型,用于识别物体或fine tune自己的网络模型(This model is made by GoogLeNet and it has been in s steady accuracy in placesCNN205 dataset. This object can be used in struct detections or fine tune your own network.)
Initial & repeat MRI in MS-Free Dataset
- matlab algorithm implementation3 data
pix2pix
- 实现论文pix2pix,目前在数据集上CMP_facade测试(implementation of pix2pix,now is testing on CMP_facade dataset)
cascadeCNN_license_plate_detection-master
- 很好的一个车牌检测程序,检测率很高,快速卷积神经网络SoftwareMatlab R2016b Matlab R2016b(plate lisence detectionMatlab lesson design for vehicle detection and recognition. Using cifar-10Net to training a RCNN, and finetune AlexNet to classify. Thanks to Cars Dataset : http:/
SVD++
- 简单的SVD基于movielens的开发python程序(this is a simple SVD write by python base on movielens dataset)
adaboost
- 其核心思想是针对同一个训练集训练不同的分类器(弱分类器),然后把这些弱分类器集合起来,构成一个更强的最终分类器(强分类器)。其算法本身是通过改变数据分布来实现的(Adaboost as an iterative algorithm which core idea is to train several different weak classifiers for the same dataset and then collect them together to form a stronger
CNTK
- 在深度的重要性的驱使下,出现了一个新的问题:训练一个更好的网络是否和堆叠更多的层一样简单呢?解决这一问题的障碍便是困扰人们很久的梯度消失/梯度爆炸,这从一开始便阻碍了模型的收敛。归一初始化(normalized initialization)和中间归一化(intermediate normalization)在很大程度上解决了这一问题,它使得数十层的网络在反向传播的随机梯度下降(SGD)上能够收敛。 当深层网络能够收敛时,一个退化问题又出现了:随着网络深度的增加,准确率达到饱和(不足为奇)然后迅
tensorflow_cov_mnist
- 基于tensorflow的mnist数据集卷积神经网络简单代码实现。(MNIST dataset based on tensorflow convolutional neural network simple code implementation)
pca
- 用户可以选择/输入,减少数据集的特征数。(User can choose/input the no.of features in the reduced Dataset.)
MNIST-PCA
- 使用PCA算法分析MNIST 手写字符训练样本。 结果分别生成以2、5、10个PCA主成分的重构图像以及10个主成分特征向量的对应图像。(Implement PCA algorithm on MNIST dataset and calculate the class PCA on each digit separately.)