無(wú)監(jiān)督學(xué)習(xí)
無(wú)監(jiān)督學(xué)習(xí)讓我們能夠在完全不知道結(jié)果的情況下處理問(wèn)題映砖，我們能夠從不知道變量的情況下從數(shù)據(jù)當(dāng)中得到結(jié)構(gòu)
能夠通過(guò)將數(shù)據(jù)中的變量進(jìn)行聚類來(lái)獲得結(jié)構(gòu)
無(wú)監(jiān)督學(xué)習(xí)沒(méi)有基于預(yù)測(cè)結(jié)果的反饋（也就是沒(méi)有訓(xùn)練集）
例子：
- 聚類：1豪治，000，000個(gè)不同的基因找到一種方式自動(dòng)將這些基因分成以不同變量分開(kāi)的相似幾組
- 非聚類：雞尾酒派對(duì)算法，在混亂環(huán)境中找到結(jié)構(gòu)宽气，從各種不同聲音中辨別獨(dú)立的人聲和音樂(lè)https://en.wikipedia.org/wiki/Cocktail_party_effect
常見(jiàn)Q&A
Q: Why do we have to use Matlab or Octave? Why not Clojure, Julia, Python, R or [Insert favourite language here]?A: As Prof. Ng explained in the 1st video of the Octave tutorial, he has tried teaching Machine Learning in a variety of languages, and found that students come up to speed faster with Matlab/Octave. Therefore the course was designed using Octave/Matlab, and the automatic submission grader uses those program interfaces. Octave and Matlab are optimized for rapid vectorized calculations, which is very useful in Machine Learning. R is a nice tool, but:
- It is a bit too high level. This course shows how to actually implement the algorithms of machine learning, while R already has them implemented. Since the focus of this course is to show you what happens in ML algorithms under the hood, you need to use Octave 2. This course offers some starter code in Octave/Matlab, which will really save you tons of time solving the tasks.
看來(lái)這門課程旨在揭開(kāi)機(jī)器學(xué)習(xí)算法底下的面紗改化，Matlab和Octave在向量計(jì)算上非常快捷哮伟，并且在學(xué)習(xí)補(bǔ)充算法的時(shí)候比較方便干花，但是在R上使用這些算法，這些算法已經(jīng)補(bǔ)充完全了楞黄，也就是說(shuō)學(xué)不到任何東西把敢，和剛才說(shuō)的課程初衷相悖。
2.怎么輸入答案谅辣？
回答：一維的矩陣不寫括號(hào)修赞，小數(shù)點(diǎn)最多寫兩位小數(shù)，分?jǐn)?shù)只能寫成小數(shù)形式桑阶，
3.Q: My quiz grade displayed is wrong or I have a verification issue or I cannot retake a quiz. What should I do? A: Contact Help Center. These queries can only be resolved by learner support and it is best if they are contacted directly.
