Machine Learning Week_1 Welcome
0 Welcome
0.1 Video: Welcome to Machine Learning!
Transcript
What is machine learning? You probably use it dozens of times a day without even knowing it.
Each time you do a web search on Google or Bing, that works so well because their machine learning software has figured out how to rank what pages. When Facebook or Apple's photo application recognizes your friends in your pictures, that's also machine learning.
Each time you read your email and a spam filter saves you from having to wade through tons of spam, again, that's because your computer has learned to distinguish spam from non-spam email.
So, that's machine learning.
There's a science of getting computers to learn without being explicitly programmed.
One of the research projects that I'm working on is getting robots to tidy up the house. How do you go about doing that? Well what you can do is have the robot watch you demonstrate the task and learn from that. The robot can then watch what objects you pick up and where to put them and try to do the same thing even when you aren't there.
For me, one of the reasons I'm excited about this is the AI, or artificial intelligence problem. Building truly intelligent machines, we can do just about anything that you or I can do. Many scientists think the best way to
make progress on this is through learning algorithms called neural networks, which mimic how the human brain works, and I'll teach you about that, too.
In this class, you learn about machine learning and get to implement them yourself. I hope you sign up on our website and join us.
unfamiliar words
explicit [ɪkˈsplɪsɪt]
- ADJ Something that is explicit is expressed or shown clearly and openly, without any attempt to hide anything.
explicitly [ɪkˈsplɪsɪtli]
demonstrate [ˈdemənstreɪt]
V-T To demonstrate a fact means to make it clear to people.
V-T If you demonstrate something, you show people how it works or how to do it.
eg. A selection of cosmetic companies will be there to demonstrate their new products
mimic [ˈmɪmɪk]
- V-T If someone or something mimics another person or thing, they try to be like them.
eg. The computer doesn't mimic human thought; it reaches the same ends by different means.
implement [ˈɪmplɪment]
V-T to make sth that has been officially decided start to happen or be used
- to implement changes/decisions/policies/reforms(改革)
N-COUNT An implement is a tool or other piece of equipment.
eg. writing implements
0.2 Reading: Machine Learning Honor Code
We strongly encourage students to form study groups, and discuss the lecture videos (including in-video questions). We also encourage you to get together with friends to watch the videos together as a group. However, the answers that you submit for the review questions should be your own work. For the programming exercises, you are welcome to discuss them with other students, discuss specific algorithms, properties of algorithms, etc.;
We ask only that you not look at any source code written by a different student, nor show your solution code to other students.
Guidelines for Posting Code in Discussion Forums
Scenario 1: Code to delete
Learner Question/Comment: "Here is the code I have so far, but it fails the grader. Please help me fix it."
Why Delete?: The reason is that if there is a simple fix provided by a student, a quick copy and paste with a small edit will provide credit without individual effort.
Learner Question: A student substitutes words for the math operators, but includes the variable names (or substitutes the equivalent greek letters (θ for 'theta', etc). This student also provides a sentence-by-sentence, line by line, description of exactly what their code implements. "The first line of my script has the equation "hypothesis equals theta times X", but I get the following error message...".
Why Delete?: This should be deleted. “Spelling out” the code in English is the same as using the regular code.
Scenario 2: Code not to delete
Learner Question: How do I subset a matrix to eliminate the intercept?
Mentor Response: This probably would be okay, especially if the person posting makes an effort to not use familiar variable names, or to use a context which has nothing to do with the contexts in the assignments.
It is clearly ok to show examples of Octave code to demonstrate a technique. Even if the technique itself is directly applicable to a programming problem at hand. As long as what is typed cannot be "cut and pasted" into the program at hand.
E.g. how do I set column 1 of a matrix to zero? Try this in your Octave work area:
>> A = magic(3)
>> A(:,1) = 0
The above is always acceptable (in my understanding). Demonstrating techniques and learning the language/syntax are important Forum activities.
unfamiliar words
Forum [ˈfɔːrəm]
- N-COUNT A forum is a place, situation, or group in which people exchange ideas and discuss issues, especially important public issues.
lecture [ˈlektʃər]
- N-COUNT A lecture is a talk someone gives in order to teach people about a particular subject, usually at a university or college.
property [ˈprɒpəti] properties ['prɒpətɪz]
N-UNCOUNT Someone's property is all the things that belong to them or something that belongs to them.
eg. Richard could easily destroy her personal property to punish her for walking out on him.N-COUNT The properties of a substance or object are the ways in which it behaves in particular conditions.
eg. A radio signal has both electrical and magnetic properties.
Scenario [səˈnærioʊ]
- N-COUNT If you talk about a likely or possible scenario, you are talking about the way in which a situation may develop.
eg. Let me suggest a possible scenario.
provide credit
- N-COUNT Recognition by a college or university that a course of studies has been successfully completed; typically measured in semester hours. At universities and colleges you need a certain number of credits to be awarded a degree.
substitute [ˈsʌbstɪtjuːt] substitutes [ˈsʌbstɪtjuːts]
- N-COUNT A substitute is something that you have or use instead of something else.
eg. She is seeking a substitute for the very man whose departure made her cry.
equivalent [ɪˈkwɪvələnt] greek letters
- N-SING If one amount or value is the equivalent of another, they are the same.
regular code.
ADJ Regular is used to mean "normal.
eg. The product looks and burns like a regular cigarette.ADJ Regular events have equal amounts of time between them, so that they happen, for example, at the same time each day or each week.
eg. Get regular exercise.
subset [ˈsʌbset]
- N-COUNT A subset of a group of things is a smaller number of things that belong together within that group.
terminate [ˈtɜːmɪneɪt]
- V-T/V-I When you terminate something or when it terminates, it ends completely.
eg. Her next remark abruptly terminated the conversation.
eliminate [ɪˈlɪmɪneɪt]
- V-T To eliminate something, especially something you do not want or need, means to remove it completely.
intercept [ˌɪntərˈsept] 截距[mathematical],拦截
- V-T If you intercept someone or something that is travelling from one place to another, you stop them before they get to their destination.
Machine Learning Week_1 Welcome的更多相关文章
- 【Machine Learning】KNN算法虹膜图片识别
K-近邻算法虹膜图片识别实战 作者:白宁超 2017年1月3日18:26:33 摘要:随着机器学习和深度学习的热潮,各种图书层出不穷.然而多数是基础理论知识介绍,缺乏实现的深入理解.本系列文章是作者结 ...
- 【Machine Learning】Python开发工具:Anaconda+Sublime
Python开发工具:Anaconda+Sublime 作者:白宁超 2016年12月23日21:24:51 摘要:随着机器学习和深度学习的热潮,各种图书层出不穷.然而多数是基础理论知识介绍,缺乏实现 ...
- 【Machine Learning】机器学习及其基础概念简介
机器学习及其基础概念简介 作者:白宁超 2016年12月23日21:24:51 摘要:随着机器学习和深度学习的热潮,各种图书层出不穷.然而多数是基础理论知识介绍,缺乏实现的深入理解.本系列文章是作者结 ...
- 【Machine Learning】决策树案例:基于python的商品购买能力预测系统
决策树在商品购买能力预测案例中的算法实现 作者:白宁超 2016年12月24日22:05:42 摘要:随着机器学习和深度学习的热潮,各种图书层出不穷.然而多数是基础理论知识介绍,缺乏实现的深入理解.本 ...
- 【机器学习Machine Learning】资料大全
昨天总结了深度学习的资料,今天把机器学习的资料也总结一下(友情提示:有些网站需要"科学上网"^_^) 推荐几本好书: 1.Pattern Recognition and Machi ...
- [Machine Learning] Active Learning
1. 写在前面 在机器学习(Machine learning)领域,监督学习(Supervised learning).非监督学习(Unsupervised learning)以及半监督学习(Semi ...
- [Machine Learning & Algorithm]CAML机器学习系列2:深入浅出ML之Entropy-Based家族
声明:本博客整理自博友@zhouyong计算广告与机器学习-技术共享平台,尊重原创,欢迎感兴趣的博友查看原文. 写在前面 记得在<Pattern Recognition And Machine ...
- machine learning基础与实践系列
由于研究工作的需要,最近在看机器学习的一些基本的算法.选用的书是周志华的西瓜书--(<机器学习>周志华著)和<机器学习实战>,视频的话在看Coursera上Andrew Ng的 ...
- matlab基础教程——根据Andrew Ng的machine learning整理
matlab基础教程--根据Andrew Ng的machine learning整理 基本运算 算数运算 逻辑运算 格式化输出 小数位全局修改 向量和矩阵运算 矩阵操作 申明一个矩阵或向量 快速建立一 ...
- Machine Learning
Recently, I am studying Maching Learning which is our course. My English is not good but this course ...
随机推荐
- 树莓派3b+ 安装windows10 arm版本的方法及使用体验
首先,我再网上找到了一个很详细的为树莓派3b安装windows10 arm的教程,实际操作下来发现并不可行. 最后找到了可行的教程: 第3章 将Windows10镜像写入TF卡:https://zhu ...
- 新晋 Committer!来自复旦大学的帅哥一枚
点亮Star️ · 支持我们 https://github.com/apache/dolphinscheduler 最近,社区星力量又迎来一位新晋 Committer,这次是来自复旦大学研究生在读的王 ...
- .Net Aspire次体验
上次用上了在微软MVP的带领下用上了Aspire,在开发阶段隐藏了细节,什么都不用做,点个调试按钮就跑起来了,可是部署时出现了难题, 因为发布时只能选择Azure环境,为此注册了Azure,开了科网. ...
- Linux信号量(1)-SYSTEM V
信号量概念 信号量本质上是一个计数器(不设置全局变量是因为进程间是相互独立的,而这不一定能看到,看到也不能保证++引用计数为原子操作),用于多进程对共享数据对象的读取,它和管道有所不同,它不以传送 ...
- 基于surging的产品项目-木舟开源了!
一 . 概述 因为前段时间电脑坏了,导致代码遗失,踌躇满志马上上线的平台产品付之东流,现在熬夜在写代码希望能尽快推出企业正常使用的平台产品,而这次把代码开源,一是让大家对surging 使用有个深入的 ...
- Dapr v1.14 版本已发布
Dapr是一套开源.可移植的事件驱动型运行时,允许开发人员轻松立足云端与边缘位置运行弹性.微服务.无状态以及有状态等应用程序类型.Dapr能够确保开发人员专注于编写业务逻辑,而不必分神于解决分布式系统 ...
- 如何将png转为svg
如何将png转为svg如图所示. 工具/原料 Inkscape 方法/步骤 1 打开Inkscape,"文件-打开"如图. 2 打开你需要转化的png图片.如图所示. 3 打开你 ...
- SSH 登陆 Windows 时踩过的坑
有一次处于某些原因我在 Mac 上使用 SSH 远程登陆了 Windows,然后在 Windows 上使用 SSH 登陆 localhost,惊讶地发现登不进去!SSH 提示公钥验证失败.可是我的 W ...
- 搭建MyBatis环境
开发环境 idea .maven .MySQL.MyBatis MySQL不同版本的注意事项 1.驱动类driver-class-name MySQL 5版本使用jdbc5驱动,驱动类使用:com.m ...
- seata 下载及安装
分布式事务 参考文章: 分布式事务实战方案汇总 https://www.cnblogs.com/yizhiamumu/p/16625677.html 分布式事务原理及解决方案案例https://www ...