深度学习文档1.0

Deep Learning Tutorials

翻译 ： 凌风探梅，转载请保留本行

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. See these course notes for a brief introduction to Machine Learning for AI and an introduction to Deep Learning algorithms.

深度学习是机器学习研究的一个新领域，它让机器学习更接近它的原始目标之一：人工智能。请看一下这些课程《人工智能中的机器学习简介》和《深度学习算法简介》。

Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. For more about deep learning algorithms, see for example:

深度学习通过学习多层次的表示和抽象，使的图像、声音和文本等数据有意义。有关深度学习算法的更多内容，参见如下：

• The monograph or review paper Learning Deep Architectures for AI (Foundations & Trends in Machine Learning, 2009).
• 专著或者综述论文《人工智能中的深度架构学习》(Foundations & Trends in Machine Learning, 2009)

• The ICML 2009 Workshop on Learning Feature Hierarchies webpage has a list of references.
• ICML 2009研讨会官员学习特征层次的主页有一个参考文献列表

• The LISA public wiki has a reading list and a bibliography.
• LISA公共 wiki主页有一个阅读列表和一个书目提要

• Geoff Hinton has readings from 2009’s NIPS tutorial.
• 2009年NIPS教程上读物

The tutorials presented here will introduce you to some of the most important deep learning algorithms and will also show you how to run them using Theano. Theano is a python library that makes writing deep learning models easy, and gives the option of training them on a GPU.

本教程将向你介绍一些最重要的深度学习算法，另外还将展示如何使用Theano运行这些算法。Theano 是一个Python库，这使得写一个深度学习模型变得很简单，并且可以选在GPU上训练这些算法。

The algorithm tutorials have some prerequisites. You should know some python, and be familiar with numpy. Since this tutorial is about using Theano, you should read over the Theano basic tutorial first. Once you’ve done that, read through our Getting Started chapter – it introduces the notation, and [downloadable] datasets used in the algorithm tutorials, and the way we do optimization by stochastic gradient descent.

本算法教程有一些前提条件。你需要对python哟一定的了解，并且熟悉numpy。因为本教程是关于如何使用Theano的，你应该首先读一下《Theano基本教程》。如果你已经完成了这些，请开始阅读我们的开始章节——介绍了算法教程中使用的符号、[可下载的]数据库，和通过梯度下降法做优化的方法。

The purely supervised learning algorithms are meant to be read in order:

按顺序阅读纯监督式学习算法：

               1. Logistic Regression - using Theano for something simple

                逻辑回归 - 用Theano做一些简单的例子

     2.  Multilayer perceptron - introduction to layers

        多层感知器 - 介绍层

     3. Deep Convolutional Network - a simplified version of LeNet5

         深度卷积网络 - LeNet的一个简化版本

The unsupervised and semi-supervised learning algorithms can be read in any order (the auto-encoders can be read independently of the RBM/DBN thread):

非监督式和半监督式学习算法可以按照随意的顺序阅读(RBM/DBN的自动编码可以独立的阅读)：

• Auto Encoders, Denoising Autoencoders - description of autoencoders
• 自动编码，降噪自动编码器 - 自动编码器的描述

• Stacked Denoising Auto-Encoders - easy steps into unsupervised pre-training for deep nets
• 堆叠的降噪自动编码器 - 深度网络的非监督式预训练简单步骤

• Restricted Boltzmann Machines - single layer generative RBM model
• 限制波尔兹曼机 - 单层generative RBM模型

• Deep Belief Networks - unsupervised generative pre-training of stacked RBMs followed by supervised fine-tuning
• 深度置信网络 - 堆叠式RBMs的非监督式生成预训练和监督式调优。

Building towards including the mcRBM model, we have a new tutorial on sampling from energy models:

对包括mcRBM模型的建立，我们有一个来自能量模型的新教程：

• HMC Sampling - hybrid (aka Hamiltonian) Monte-Carlo sampling with scan()
• HMC采样 - (又名汉密尔顿)混合蒙特卡罗抽样 with scan()

        

Building towards including the Contractive auto-encoders tutorial, we have the code for now:

缩减性自动编码教程，代码如下|：

• Contractive auto-encoders code - There is some basic doc in the code.
• 缩减性自动编码代码- 代码中有一些基本的文档

Recurrent neural networks with word embeddings and context window:

• Semantic Parsing of Speech using Recurrent Net
• 使用递归网的语音语义分析
  

LSTM network for sentiment analysis:

使用LSTM网络的情感分析:

• LSTM network
• LSTM 网络

Energy-based recurrent neural network (RNN-RBM):

基于能量的递归神经网络(RNN-RBM)：

• Modeling and generating sequences of polyphonic music
• 使用RNN-RBMs多声道复条音乐的建模和序列产生
  

Note that the tutorials here are all compatible with Python 2 and 3, with the exception of Modeling and generating sequences of polyphonic music with the RNN-RBM which is only available for Python 2.

本教程的内容完全兼容Python 2 和 3，其中《使用RNN-RBMs多声道复条音乐的建模和序列产生》只兼容Python 2