• This repository has been archived on 27/Feb/2021
  • Stars
    star
    337
  • Rank 125,272 (Top 3 %)
  • Language
  • License
    Apache License 2.0
  • Created about 9 years ago
  • Updated over 6 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

[UNMAINTAINED] 非监督特征学习与深度学习中文教程,该版本翻译自新版 UFLDL Tutorial 。建议新人们去学习斯坦福的CS231n课程,该门课程在网易云课堂上也有一个配有中文字幕的版本。

注意:这个项目我不再维护,我觉得我的翻译真的不够好来帮助其他人,尤其是那些刚入门或者刚开始学习了解深度学习、神经网络的人们。为了不误导其他人,我建议新人们去学习斯坦福的CS231n课程,该门课程在网易云课堂上也有一个配有中文字幕的版本。 Have fun!

为了极佳的阅读体验,您可点击 这里 将本文档下载到本地,并安装 Haroopad 进行阅读。

非监督特征学习与深度学习 中文教程

中文版的新版 UFLDL 教程(项目地址: www.github.com/ysh329/Chinese-UFLDL-Tutorial ),该版本翻译自 UFLDL Tutorial ,是新版教程的翻译。也可参考 旧版 UFLDL 中文教程 。翻译过程中有一些数学公式,使用 Haroopad 编辑和排版, Haroopad 是一个优秀的离线 MarkDown 编辑器,支持 TeX 公式编辑,支持多平台(Win/Mac/Linux),目前还在翻译中,翻译完成后会考虑使用 TeX 重新排版。

自己对新版 UFLDL 教程翻译过程中,发现的英文错误,见 新版教程英文原文勘误表

注: UFLDL 是非监督特征学习及深度学习(Unsupervised Feature Learning and Deep Learning)的缩写,而不仅指深度学习(Deep Learning)。

  • 翻译者:Shuai Yuan ,部分小节参考旧版翻译进行修正和补充。
  • 若有翻译错误,请直接 New issue发邮件 ,感谢!

更多详细参考资料,见 计算机科学人工智能机器学习深度学习强化学习深度强化学习公开数据集

欢迎来到新版 UFLDL 中文教程!

说明:本教程将会教给您非监督特征学习以及深度学习的主要思想。通过它,您将会实现几个特征学习或深度学习的算法,看到这些算法为您(的工作)带来作用,以及学习如何将这些思想应用到适用的新问题上。

本教程假定您已经有了基本的机器学习知识(具体而言,熟悉监督学习,逻辑斯特回归以及梯度下降法的思想)。如果您不熟悉这些,我们建议您先去 机器学习课程 中去学习,并完成其中的第II,III,IV章节(即到逻辑斯特回归)。

材料由以下人员提供:Andrew Ng, Jiquan Ngiam, Chuan Yu Foo, Yifan Mai, Caroline Suen, Adam Coates, Andrew Maas, Awni Hannun, Brody Huval, Tao Wang, Sameep Tandon

获取初学者代码(Starter Code)

初学者代码

您可以获得初学者所有练习的代码从 该Github的代码仓库

有关的数据文件可以从 这里 下载。 下载到的数据需要解压到名为“common”的文件夹中(以便初学者代码的使用)。

目录

每个小节后面的[old][new][旧]分别代表:旧版英文、新版英文、旧版中文三个版本。若没有对应的版本则用[无]代替。

More Repositories

1

deep-learning-model-convertor

The convertor/conversion of deep learning models for different deep learning frameworks/softwares.
3,244
star
2

embedded-ai.bi-weekly

WeChat: NeuralTalk,Weekly report and awesome list of embedded-ai.
376
star
3

OpenCL-101

Learn OpenCL step by step.
C
130
star
4

OpenMP-101

Learn OpenMP examples step by step
C
85
star
5

statistical-learning-methods-note

李航《统计学习方法》笔记和 Python 实现(不基于任何代数运算库)。
Python
59
star
6

darknet2caffe

Convert Darknet model to Caffe's
Python
49
star
7

android-reverse-engineering

android-reverse-engineering
26
star
8

Douban-Crawler

抓取豆瓣小组相关信息(小组、用户、帖子)。
Python
24
star
9

link-prediction

[UNMAINTAINED] 基于PySpark与MySQL的复杂网络链路预测。
Python
21
star
10

sword-x-offer

66 classic and common interview problems from 《剑指offer》 with multiple-method-CPP solutions, and common data structure summary, etc
20
star
11

awesome-deep-learning-finetune-experience

This repository not only contains experience about parameter finetune, but also other in-practice experience such as model ensemble (boosting, bagging and stacking) in Kaggle or other competitions.
16
star
12

cv-template

LaTeX resume template
7
star
13

deep-learning-model-archtecture-design-advice

6
star
14

git-101

5
star
15

kaggle-cervical-cancer-screening-classification

Solution and summary for Intel & MobileODT Cervical Cancer Screening (3-class classification)
Jupyter Notebook
5
star
16

Chatter-Bot-CN

基于ChatterBot框架,做一个中文聊天机器人。
Python
5
star
17

logging

A light-weight C++ logging for mobile.
C++
5
star
18

kaggle-lung-cancer-classification

kaggle data science bowl 2017 solution
Jupyter Notebook
4
star
19

naive-binary-gemm

C
3
star
20

caffe-tools

Python
3
star
21

spam-msg-classifier

A spam message classifier based on Naive Bayes.
Python
3
star
22

add-license-for-repo

Add license content for each file in repository recursively
Python
2
star
23

Chinese-word-segmentation

Accomplish Chinese word segmentation by Python.
Python
2
star
24

tmp

C++
2
star
25

stock-newspaper-crawler

[UNMAINTAINED]Crawl 4 kinds of finance newspaper corpus (from CCSTOCK.CN).
Python
2
star
26

tiny-deep-learning-models

fast, tiny deep learning models for mobile and embedded devices
2
star
27

pyTextRank

基于 PageRank 的关键词提取,关键句子提取(摘要)算法的 Python 实现。此外,还有一个基于此的句子相似度算法。
Jupyter Notebook
2
star
28

flask-test

Python
1
star
29

docker-101

1
star
30

monitor

Monitor service status and restart if service dead
Python
1
star
31

Django-TODO

A TODO list project by Django
Python
1
star
32

kaggle-dog-cat-classification

1
star
33

ysh329

1
star
34

software-config

Configures including vim, Xshell and etc.
Vim Script
1
star
35

conv-scale

1
star
36

deXtop

A desktop tool automaticly switching wallpapers on Ubuntu 16.04.
Python
1
star
37

build-101

CMake
1
star
38

deep-learning-operator

implementation, benchmark, optimization
C
1
star
39

Titanic-Machine-Learning-from-Disaster

In this challenge, we ask you to complete the analysis of what sorts of people were likely to survive. In particular, we ask you to apply the tools of machine learning to predict which passengers survived the tragedy.
Python
1
star
40

wordsDB

As the march of project Chinese-word-segmentation, I found that I should create and sustain a words database first. In this projec, mainly concentrating on the general words (come from modern Chinese dictionary, which as the first part) and professional words about financial, stock, fund and economics aspects.
Python
1
star