What is Machine Learning?

author: Neil D. Lawrence, Department of Computer Science, University of Sheffield
published: May 13, 2013,   recorded: April 2012,   views: 3883
Categories

Slides

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Delicious Bibliography

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:07:54
!NOW PLAYING
Watch Part 2
Part 2 1:05:15
!NOW PLAYING

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 George Spilkov, August 7, 2013 at 9:50 p.m.:

So ... what is Machine Learning?
It is definitely not this. This is not a true Machine Learning.

My definition is: Machine Learning is when a system has the ability to formulate 'sensible' questions and then include the answers into asking more questions thus growing its knowledge base and improving its ability to provide answers.

The definition is closer to that of Arthur Samuel than to the one given by Tom M. Mitchell - which seems to be the one used in this lecture.

Everything we humans learn starts with a question. The first step in the scientific method is the question, and then comes the hypothesis.

That is why I say, let focus on building systems capable of asking questions instead of systems that provide answers.

Knowledge is like a coral reef - the answers are the dead part of the reef and the questions are the live layer of the reef. Eventually the questions become answers and the knowledge grows as does the coral reef.

Even toddlers ask questions with the tone of their voice before they can formulate any words/answers.

I think the phrase 'Machine Learning' got hijacked from its true meaning. The knowledge domain we propagate today as 'machine learning' is not what will make the machines 'learn' in the true sense of the word 'learn'.

Write your own review or comment:

make sure you have javascript enabled or clear this field: