本文为《DeepLearning 0.1 documentation》的中文翻译,本人水平有限,如有错误或不当,欢迎批评指正!非常感谢!
原文网址:http://deeplearning.net/tutorial/contents.html
注:点击英文上的链接会转到原网页,点击对应中文转到翻译网页。
包括以下内容:
Contents
- LICENSE(许可)
- Deep Learning Tutorials(深度学习教程)
- Getting Started(入门)
- Download(下载)
- Datasets(数据集)
- Notation(符号)
- A Primer on Supervised Optimization for Deep Learning(深度学习有监督优化基础)
- Theano/Python Tips
- Classifying MNIST digits using Logistic Regression(采用Logistic回归分类MNIST数字)
- The Model(模型)
- Defining a Loss Function(定义损失函数)
- Creating a LogisticRegression class(创建LogisticRegression类)
- Learning the Model(模型学习)
- Testing the model(测试模型)
- Putting it All Together(程序汇总)
- Multilayer Perceptron(多层感知器)
- The Model(模型)
- Going from logistic regression to MLP(从LG到MLP)
- Putting it All Together(汇总)
- Tips and Tricks for training MLPs(训练多层感知器的的一点提示与技巧)
- Convolutional Neural Networks (LeNet)(卷积神经网络CNN)
- Motivation
- Sparse Connectivity(稀疏连接性)
- Shared Weights(共享权重)
- Details and Notation(细节与符号)
- The Convolution Operator(卷积操作)
- MaxPooling(最大化池)
- The Full Model: LeNet(完整模型)
- Putting it All Together
- Running the Code(运行代码)
- Tips and Tricks(提示与技巧)
- Denoising Autoencoders (dA)(去噪自编码器DA)
- Autoencoders(自编码器 )
- Denoising Autoencoders(去噪自编码器)
- Putting it All Together
- Running the Code
- Stacked Denoising Autoencoders (SdA)(堆栈式去噪自编码器SDA)
- Stacked Autoencoders(堆栈式自编码器)
- Putting it all together
- Running the Code
- Tips and Tricks
- Restricted Boltzmann Machines (RBM)(受限玻尔兹曼机)
- Energy-Based Models (EBM)(基于能量的模型)
- Restricted Boltzmann Machines (RBM)
- Sampling in an RBM(RBM中的采样)
- Implementation(实现)
- Results(结果)
- Deep Belief Networks(深度信念网络)
- Deep Belief Networks
- Justifying Greedy Layer-Wise Pre-Training(证明逐层贪婪式预训练)
- Implementation
- Putting it all together
- Running the Code
- Tips and Tricks
- Hybrid Monte-Carlo Sampling(混合蒙特卡罗采样HMC)
- Theory
- Implementing HMC Using Theano(使用Theano实现HMC)
- Testing our Sampler
- References
- Recurrent Neural Networks with Word Embeddings(字嵌入经常性神经网络)
- Summary
- Code - Citations - Contact(代码 - 引文 - 联系)
- Task
- Dataset
- Recurrent Neural Network Model(经常性的神经网络模型)
- Evaluation(评估)
- Training
- Running the Code
- LSTM Networks for Sentiment Analysis(用于情感分析的LSTM网络)
- Summary
- Data
- Model
- Code - Citations - Contact(代码 - 引文 - 联系)
- References
- Modeling and generating sequences of polyphonic music with the RNN-RBM(用RNN-RBM建模并生成和弦音乐序列)
- The RNN-RBM(RNN-RBM:递归神经网络和受限玻尔兹曼机)
- Implementation
- Results
- How to improve this code(改进代码)
- Miscellaneous(杂项)
- Plotting Samples and Filters(绘制样本和过滤器)
- References