Skip to main content

Experience Management

What is Machine Learning?

What is Machine Learning?  Well, I have a general idea of how to explain Machine Learning – it is the process of training a computer using historical data and decisions, such that the computer can then make its own decisions in the future using all new data that it has never seen before.  For example, machine learning is used to train computers to read handwriting by studying countless examples of known writing samples.  It is also used to study market data and make predictions about when to buy or sell.
lettersThis has given me a pretty good “black-box” understanding of machine learning algorithms.  I understand that you feed in a bunch of data along with historical decisions and outcomes.  Then a miracle occurs.  And now the machine can make its own decisions in the future.  If I feed the black box a million different handwritten letter A’s, and I tell it that all of them are the letter A, it should now be able to see a letter that it has never seen before and tell me with some confidence whether or not it is a letter A.
But, until yesterday, I had no idea what was going on inside the black box.  What techniques are actually used to train and program machine learning applications?  How can a computer “think” about input and make a yes or no decision?
I read a fascinating article that provides a very good introduction to Machine Learning.  The authors have used images, animations, and text in perfect combination to explain a difficult subject.  Candidly, it’s one of the best technical writings I have seen in a long time.  If you are interesting in learning more about what is inside the Machine Learning “black box”, I highly recommend reading this article:
 

machine learningA Visual Introduction to Machine Learning

http://www.r2d3.us/visual-intro-to-machine-learning-part-1/
In machine learning, computers apply statistical learning techniques to automatically identify patterns in data. These techniques can be used to make highly accurate predictions.
Keep scrolling. Using a data set about homes, we will create a machine learning model to distinguish homes in New York from homes in San Francisco.
 
 

In a future post, I will give some concrete applications of machine learning that we are using in our Enterprise Search projects at Perficient.  Stay tuned!
 

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Chad Johnson

Chad is a Principal of Search and Knowledge Discovery at Perficient. He was previously the Director of Perficient's national Google for Work practice.

More from this Author

Follow Us
TwitterLinkedinFacebookYoutubeInstagram