Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint
Share this Page URL
Help

3. Discovering Groups > Supervised versus Unsupervised Learning

Supervised versus Unsupervised Learning

Techniques that use example inputs and outputs to learn how to make predictions are known as supervised learning methods. We’ll explore many supervised learning methods in this book, including neural networks, decision trees, support-vector machines, and Bayesian filtering. Applications using these methods “learn” by examining a set of inputs and expected outputs. When we want to extract information using one of these methods, we enter a set of inputs and expect the application to produce an output based on what it has learned so far.

Clustering is an example of unsupervised learning. Unlike a neural network or a decision tree, unsupervised learning algorithms are not trained with examples of correct answers. Their purpose is to find structure within a set of data where no one piece of data is the answer. In the fashion example given earlier, the clusters don’t tell the retailers what an individual is likely to buy, nor do they make predictions about which fashion island a new person fits into. The goal of clustering algorithms is to take the data and find the distinct groups that exist within it. Other examples of unsupervised learning include non-negative matrix factorization, which will be discussed in Chapter 10, and self-organizing maps.


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free 10-Day Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint