Deep Learning Tutorials

翻譯 ： 凌風探梅，轉(zhuǎn)載請保留本行

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.

深度學習是機器學習研究的一個新領(lǐng)域，它讓機器學習更接近它的原始目標之一：人工智能。請看一下這些課程《人工智能中的機器學習簡介》和《深度學習算法簡介》。

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:

深度學習通過學習多層次的表示和抽象，使的圖像、聲音和文本等數(shù)據(jù)有意義。有關(guān)深度學習算法的更多內(nèi)容，參見如下：

• The monograph or review paper?Learning Deep Architectures for AI?(Foundations & Trends in Machine Learning, 2009).
• 專著或者綜述論文《人工智能中的深度架構(gòu)學習》(Foundations & Trends in Machine Learning, 2009)

• The ICML 2009 Workshop on Learning Feature Hierarchies?webpage?has a?list of references.
• ICML 2009研討會官員學習特征層次的主頁有一個參考文獻列表

• The LISA?public wiki?has a?reading list?and a?bibliography.
• LISA公共 wiki主頁有一個閱讀列表和一個書目提要

• Geoff Hinton has?readings?from 2009’s?NIPS tutorial.
• 2009年NIPS教程上讀物

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.

本教程將向你介紹一些最重要的深度學習算法，另外還將展示如何使用Theano運行這些算法。Theano?是一個Python庫，這使得寫一個深度學習模型變得很簡單，并且可以選在GPU上訓練這些算法。

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條件。你需要對python喲一定的了解，并且熟悉numpy。因為本教程是關(guān)于如何使用Theano的，你應該首先讀一下《Theano基本教程》。如果你已經(jīng)完成了這些，請開始閱讀我們的開始章節(jié)——介紹了算法教程中使用的符號、[可下載的]數(shù)據(jù)庫，和通過梯度下降法做優(yōu)化的方法。

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

按順序閱讀純監(jiān)督式學習算法：

? ? ? ? ? ? ? ?1.?Logistic Regression?- using Theano for something simple

? ? ? ? ? ? ? ??邏輯回歸 - 用Theano做一些簡單的例子

2. ?Multilayer perceptron?- introduction to layers 多層感知器 - 介紹層
3.?Deep Convolutional Network?- a simplified version of LeNet5 ? ? ? ? ?深度卷積網(wǎng)絡 - LeNet的一個簡化版本

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):

非監(jiān)督式和半監(jiān)督式學習算法可以按照隨意的順序閱讀(RBM/DBN的自動編碼可以獨立的閱讀)：

• Auto Encoders, Denoising Autoencoders?- description of autoencoders
• 自動編碼，降噪自動編碼器?- 自動編碼器的描述

• Stacked Denoising Auto-Encoders?- easy steps into unsupervised pre-training for deep nets
• 堆疊的降噪自動編碼器 - 深度網(wǎng)絡的非監(jiān)督式預訓練簡單步驟

• Restricted Boltzmann Machines?- single layer generative RBM model
• 限制波爾茲曼機 - 單層generative RBM模型

• Deep Belief Networks?- unsupervised generative pre-training of stacked RBMs followed by supervised fine-tuning
• 深度置信網(wǎng)絡 - 堆疊式RBMs的非監(jiān)督式生成預訓練和監(jiān)督式調(diào)優(yōu)。

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

對包括mcRBM模型的建立，我們有一個來自能量模型的新教程：

• HMC Sampling?- hybrid (aka Hamiltonian) Monte-Carlo sampling with scan()
• HMC采樣 - (又名漢密爾頓)混合蒙特卡羅抽樣 with scan()

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

縮減性自動編碼教程，代碼如下|：

• Contractive auto-encoders?code - There is some basic doc in the code.
• 縮減性自動編碼代碼- 代碼中有一些基本的文檔

Recurrent neural networks with word embeddings and context window:

• Semantic Parsing of Speech using Recurrent Net
• 使用遞歸網(wǎng)的語音語義分析
  

LSTM network for sentiment analysis:

使用LSTM網(wǎng)絡的情感分析:

• LSTM network
• LSTM 網(wǎng)絡

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

基于能量的遞歸神經(jīng)網(wǎng)絡(RNN-RBM)：

• Modeling and generating sequences of polyphonic music
• 使用RNN-RBMs多聲道復條音樂的建模和序列產(chǎn)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.

本教程的內(nèi)容完全兼容Python 2 和 3，其中《使用RNN-RBMs多聲道復條音樂的建模和序列產(chǎn)生》只兼容Python 2

總結(jié)

以上是生活随笔為你收集整理的深度学习文档1.0的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。