Deep Learning 实战教程

Deep Learning 实战教程

本文包含中英翻译，显示：中文 English

引言：神经网络（Neural Network）与支持向量机（Support Vector Machines，SVM）是统计学习的代表方法。可以认为神经网络与支持向量机都源自于感知机（Perceptron）。感知机是1958年由Rosenblatt发明的线性分类模型。感知机对线性分类有效，但现实中的分类问题通常是非线性的。

神经网络与支持向量机（包含核方法）都是非线性分类模型。1986年，Rummelhart与McClelland发明了神经网络的学习算法Back Propagation。后来，Vapnik（Vladimir Vapnik 弗拉基米尔·万普尼克 ）等人于1992年提出了支持向量机。神经网络是多层（通常是三层）的非线性模型，支持向量机利用核技巧把非线性问题转换成线性问题。

神经网络与支持向量机一直处于“竞争”关系。

Scholkopf是Vapnik的大弟子，支持向量机与核方法研究的领军人物。据Scholkopf说，Vapnik当初发明支持向量机就是想"干掉"神经网络（He wanted to kill Neural Network)。支持向量机确实很有效，一段时间支持向量机一派占了上风。

近年来，神经网络一派的大师Hinton又提出了神经网络的Deep Learning算法（2006年），使神经网络的能力大大提高，可与支持向量机一比。

Deep Learning假设神经网络是多层的，首先用Boltzman Machine（非监督学习）学习网络的结构，然后再通过Back Propagation（监督学习）学习网络的权值。

关于Deep Learning的命名，Hinton曾开玩笑地说: I want to call SVM shallow learning. (注：shallow 有肤浅的意思)。其实Deep Learning本身的意思是深层学习，因为它假设神经网络有多层。

总之，Deep Learning是值得关注的统计学习新算法。

Deep Learning 实战教程

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（Deep Learning）是ML研究中的一个新的领域，它被引入到ML中使ML更接近于其原始的目标：AI。查看课程记录 for a brief introduction to Machine Learning for AI and anintroduction to Deep Learning algorithms.

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:

深度学习是关于学习多个表示和抽象层次，这些层次帮助解释数据，例如图像，声音和文本。对于更多的关于深度学习算法的知识，可以参看：

• The monograph or review paper Learning Deep Architectures for AI (Foundations & Trends in Machine Learning, 2009).</span>
• The ICML 2009 Workshop on Learning Feature Hierarchies webpage has a list of references.
• The LISA public wiki has a reading list and a bibliography.
• Geoff Hinton has readings from last year’s NIPS tutorial.

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.

本教程主要是介绍一些最重要的深度学习算法，并将演示如何用Theano来运行它们。Theano是一个python库，使得写深度学习模型更加容易，同时也给出了一些关于在GPU上训练它们的选项。

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.

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

1. Logistic Regression - using Theano for something simple
2. Multilayer perceptron - introduction to layers
3. Deep Convolutional Network - a simplified version of LeNet5

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):

• Auto Encoders, Denoising Autoencoders - description of autoencoders
• Stacked Denoising Auto-Encoders - easy steps into unsupervised pre-training for deep nets
• Restricted Boltzmann Machines - single layer generative RBM model
• Deep Belief Networks - unsupervised generative pre-training of stacked RBMs followed by supervised fine-tuning

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

• HMC Sampling - hybrid (aka Hamiltonian) Monte-Carlo sampling with scan()

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

• Contractive auto-encoders code - There is some basic doc in the code.

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

• Modeling and generating sequences of polyphonic music

翻译

【声明】 本教程为翻译 http://deeplearning.net/tutorial/，转载请注明来源。本翻译力求信达。