资源列表
Softmax_exercise
- Softmax用于多分类问题，本例是将MNIST手写数字数据库中的数据0-9十个数字进行分类，其中训练样本有6万个，测试样本有1万个数字是0~9-Softmax for multi classification problems, the present case is the handwritten data MNIST digital 0-9, classification, training samples which have 60,000, there are 10,000 test
ExerciseSelf-Taught-Learning
- Soft-taught leaning是用的无监督学习来学习到特征提取的参数，然后用有监督学习来训练分类器.-Soft-taught leaning unsupervised learning is to learn the parameters of feature extraction, followed by supervised learning to train the classifier.
MNIST数据集
- 利用pycharm对mnist数据哭进行直接解压缩操作，得到所有的图片和标签(Using pycharm to wept MNIST data directly, get all the pictures and labels)
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
LabelMeToolbox
- LabelMe is a WEB-based image annotation tool that allows researchers to label images and share the annotations with the rest of the community
moead
- 包括近年来Q.F.ZHANG 关于基于分解的多目标优化算法的一系列的文章资料。-Including the recent QFZHANG decomposition based on multi-objective optimization of a series of articles data.
53607900Autoencoder_Code
- 用SAE 深度学习方法做的高光谱图像分析的一个例子。里面有sae方法还有高光谱图像的特征提取过程。(One example of the depth of learning to do with SAE hyperspectral image analysis. There are sae method has hyperspectral image feature extraction process)
ex5
- 机器学习 5、k - means聚类 开发环境Octave-Programming Exercise 5: K-means Clustering and Principal Component Analysis Machine Learning
MATLAB神经网络43个案例分析
- 王小川著《matlab神经网络43个案例方法分析》43个神经网络算法的案例程序，官方标准版 可调试运行(Case program of neural network algorithm)
cnn_vs2012
- 基于Mnist库的手写数字识别的C++源代码，用卷积神经网络实现-Handwritten numeral recognition Mnist library C++ source code, using convolution neural network
M3LDA
- 多模多实例多类标LDA的代码。参考文献：C.-T. Nguyen, D.-C. Zhan, and Z.-H. Zhou. Multi-modal image annotation with multi-instance multi-label LDA. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI 13), Beijing, China, 2013.