Which Of The Following Is The Foundation Technology For Web Services?

▸ Unsupervised Learning :

1. For which of the following tasks might Grand-ways clustering be a suitable algorithm
   Select all that apply.
   
   
   • Given a ready of news articles from many dissimilar news websites, find out what are the chief topics covered.

     1000-means tin cluster the articles and and then we can audit them or utilise other methods to infer what topic each cluster represents
     

   
   
   • Given historical atmospheric condition records, predict if tomorrow'due south conditions will exist sunny or rainy.
   
   
   • From the user usage patterns on a website, effigy out what different groups of users exist.

     We can cluster the users with One thousand-means to detect different, distinct groups.

   
   
   • Given many emails, you want to determine if they are Spam or Non-Spam emails.
   
   
   • Given a database of information about your users, automatically group them into different market segments.

     You lot can use K-means to cluster the database entries, and each cluster will correspond to a different market segment.

   
   
   • Given sales data from a large number of products in a supermarket, figure out which products tend to form coherent groups (say are frequently purchased together) and thus should be put on the same shelf.

     If y'all cluster the sales data with K-ways, each cluster should represent to coherent groups of items.

   
   
   • Given sales data from a large number of products in a supermarket, estimate future sales for each of these products.
   
   

---

2. Suppose we have iii cluster centroids , and .
   Furthermore, nosotros have a preparation example . After a cluster assignment
   footstep, what will exist?

---

3. M-means is an iterative algorithm, and two of the following steps are repeatedly carried out in its inner-loop. Which two?

---

4. Suppose yous take an unlabeled dataset . You run Thousand-means with l dissimilar random initializations, and obtain 50 different clusterings of the information.

   What is the recommended way for choosing which 1 of these 50 clusterings to utilise?

---

Check-out our gratis tutorials on IOT (Internet of Things):

---

5. Which of the following statements are truthful? Select all that apply.
   
   
   • On every iteration of K-ways, the cost office (the distortion office) should either stay the same or decrease; in detail, it should not increase.

     Both the cluster assignment and cluster update steps decrese the cost / baloney part, so it should never increase after an iteration of Chiliad-means.

   
   
   • A adept fashion to initialize Grand-means is to select K (distinct) examples from the training set and gear up the cluster centroids equal to these selected examples.

     This is the recommended method of initialization.

   
   
   • One thousand-Means volition always requite the same results regardless of the initialization of the centroids.
   
   
   • Once an example has been assigned to a particular centroid, it volition never be reassigned to another dissimilar centroid
   
   
   • For some datasets, the "right" or "correct" value of K (the number of clusters) can be ambiguous, and hard fifty-fifty for a human adept looking carefully at the data to decide.

     In many datasets, unlike choices of K will give unlike clusterings which announced quite reasonable. With no labels on the data, we cannot say i is improve than the other.

   
   
   • The standard manner of initializing K-ways is setting to be equal to a vector of zeros.
   
   
   • If we are worried near K-means getting stuck in bad local optima, one manner to better (reduce) this problem is if we effort using multiple random initializations.

     Since each run of K-means is independent, multiple runs tin find different optima, and some should avert bad local optima.

   
   
   • Since K-Ways is an unsupervised learning algorithm, it cannot overfit the data, and thus it is always amend to have as large a number of clusters as is computationally feasible.
   
   

---

Click here to see solutions for all Machine Learning Coursera Assignments.
&
Click here to encounter more codes for Raspberry Pi three and similar Family.
&
Click here to see more codes for NodeMCU ESP8266 and like Family unit.
&
Click here to see more codes for Arduino Mega (ATMega 2560) and similar Family unit.

Feel complimentary to ask doubts in the annotate section. I will try my best to reply it.
If yous detect this helpful past any hateful similar, comment and share the post.
This is the simplest style to encourage me to go along doing such work.

Thanks & Regards,
- APDaga DumpBox

Source: https://www.apdaga.com/2019/11/coursera-machine-learning-week-8-quiz-unsupervised-learning.html

Posted by: gaulkesumbing1949.blogspot.com

Share this post