yukong / deeplearning.ai-solutions Goto Github PK
View Code? Open in Web Editor NEWSolutions of assignments and translation to Chinese
Solutions of assignments and translation to Chinese
单从第三周的情况来看,脱离视频直接翻译英文字幕的情况有点多;由于英文字幕的质量堪忧,有不少地方都存在相当严重的误翻……
所以希望审阅or搬运的小伙伴在审阅or搬运时尽量对照视频过一遍翻译,我近期也会尽量修一修;不过我个人的能力还是很有限的,所以肯定有不少漏网之鱼……
如果有愿意校对的小伙伴的话,希望能够帮忙校对一下前两周的视频翻译,我则会先简单地修一遍第三周的视频翻译
提前感谢愿意帮忙校对的小伙伴了~
简单来说就是srt每个字幕的分隔没了,就如:
1
00:00:00.000 --> 00:00:03.195
Welcome back. Vectorization is basically
欢迎回来 向量化通常是
2
00:00:03.195 --> 00:00:07.315
the art of getting rid of explicit for loops in your code.
消除你的代码中显式循环语句的艺术
在2前面应该要留个空行的
虽然问题不大(也就一个正则替换的问题)
但是还是希望修复一下吧
在01:32处
we had to find capital Y as y1
我觉得是define
首先感谢大家的付出,小弟做了测试题之后不知道对不对,想找solution对照一下。可否抓紧把solution放上来啊?没钱买课程啊。。。
此致敬礼
这个字幕会被加到coursera上吗,如果会的话,那大概是什么时候?
大家好,我是GTC的译者Yukon~
希望大家如果有关于深度学习的不错的资料、视频等等能够提交在这个Issue下,随后我整理到 Readme 中(可署名),互相学习交流,提高深度学习姿势水平。
Enjoy coding~
大概从20秒开始出现了字幕与语音、画面不同步,字幕文件一共3分56秒而实际视频只有3分43秒,我从coursera官网下载了英文字幕发现也有这个问题。
02.What is a neural network字幕有点不同步21,22开始
我看到 Coursera 上 deeplearning.ai 已经有开始有非英语的字幕,比如 Supervised Learning with Neural Networks 已经有繁体中文版本字幕,既然这个开源项目已经完成那么多简中翻译,是否会出现在 Coursera
官网上呢?
第二周03
73
00:04:35,170 --> 00:04:38,440
the sigmoid function, it can never be bigger than one.
simoid函数 它永远不会比1大
应当为
sigmoid函数 它永远不会比1大
之前有关注你们的进展,但好像官方英文字幕的质量就很有问题。今天发现了这个东西:
由 deeplearning.ai 出品,网易引进的正版授权中文版深度学习工程师微专业课程
看了一下,就是Cousera课程的视频,网易云课堂压制了带有中英文字幕的版本,和Cousera的免费内容一样,只有视频部分,没有测验、作业和证书。
稍微看了几个印象中官方字幕有问题的地方,可以确定是经过了校正的。
希望这个信息对你们有用 :)
[('05.About this Course.srt', 1, 'utf-8'),
('02.What is a neural network.srt', 1, 'utf-8'),
('03.Supervised Learning with Neural Networks.srt', 1, 'utf-8'),
('01.Welcome.srt', 1, 'utf-8'),
('04.Why is Deep Learning taking off.srt', 1, 'utf-8'),
('06.Course Resources.srt', 1, 'UTF-8-SIG')]
[('02.Logistic Regression.srt', 1, 'UTF-8-SIG'),
('10.Gradient Descent on m Examples.srt', 1, 'UTF-8-SIG'),
('04.Gradient Descent.srt', 1, 'GB2312'),
('07.Computation graph.srt', 1, 'UTF-8-SIG'),
("14.Vectorizing Logistic Regression's Gradient Output.srt", 1, 'utf-8'),
('16.A note on python_numpy vectors.srt', 1, 'utf-8'),
('03.Logistic Regression Cost Function.srt', None, 'UTF-16LE'),
('18.Explanation of logistic regression cost function (optional).srt', 1, 'UTF-8-SIG'),
('01.Binary Classification.srt', None, 'UTF-16LE'),
('13.Vectorizing Logistic Regression.srt', 1, 'UTF-8-SIG'),
('17.Quick tour of Jupyter_iPython Notebooks.srt', 1, 'GB2312'),
('11.Vectorization.srt', 1, 'utf-8'),
('15.Broadcasting in Python.srt', 1, 'utf-8'),
('12.More Examples of Vectorization.srt', 1, 'GB2312'),
('06.More Derivative Examples.srt', 1, 'GB2312'),
('09.Logistic Regression Gradient Descent.srt', 1, 'UTF-8-SIG'),
('08.Derivatives with a Computation Graph.srt', 1, 'utf-8'),
('05.Derivatives.srt', 1, 'GB2312')]
前几个视频已经可以有繁中字幕可以看了,简中已经翻译了不少了,为什么不上传一下呢
浏览了很多已经审核通过的字幕
发现了很多问题:
提议建立审核小组重审所有字幕文件
2
00:00:02,754 --> 00:00:04,820
regression this is a learning algorithm
逻辑回归,这是一种学习算法
3
00:00:04,820 --> 00:00:07,616
that you use when the output labels why
你使用它之时就知道为什么输出标签
4
00:00:07,616 --> 00:00:09,730
in a supervised learning problem are all
在一个监督学习问题中都
5
00:00:09,730 --> 00:00:12,101
either 0 or 1 so for binary
或者是0或者是1,所以对于二元
我认为这里Ng的意思是:
This is a learning algorithm that you use when the output labels y
in a supervised learning problem are all either 0 or 1.
它(Logistic Regression)是一种学习算法,使用在当监督学习的输出标签y要么是0要么是1的情况下。
而不是您翻译的why
或者说为什么
。
谢谢!
第二周09逻辑回归的梯度下降与第二周02逻辑回归有部分内容翻译得不一样:
第二周02中参考部分
44
00:02:09,256 --> 00:02:11,471
sigmoid function applied to this quantity
由这个式子作为自变量的sigmoid函数中
第二周09中需修改部分
22
00:00:48,002 --> 00:00:51,363
follows your predictions y hat is
y~定义如下 y~=a=sigma(z)
应当为:
y~定义如下 y~=a=sigmoid(z)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.