Return to Video

Comparing Classification and Regression - Intro to Machine Learning

  • 0:00 - 0:04
    Here's a quick comparison between classification and regression.
  • 0:04 - 0:06
    We'll go into more detail in everything that I write here.
  • 0:06 - 0:08
    But I want to give you a quick overview just so
  • 0:08 - 0:10
    you know what to look out for in this lesson.
  • 0:10 - 0:14
    So the first thing I'll mention is the output type of the algorithm.
  • 0:14 - 0:16
    As you know, for supervised classification,
  • 0:16 - 0:20
    this is going to be discrete in the form of class labels.
  • 0:20 - 0:22
    For regression this is continuous.
  • 0:22 - 0:25
    Which basically means that you'll be predicting a number using a regression.
  • 0:25 - 0:29
    The next question, a very important question is what are you actually trying to
  • 0:29 - 0:33
    find when you perform a classification or a regression?
  • 0:33 - 0:37
    In the case of classification this is usually a decision boundary.
  • 0:37 - 0:40
    And then depending on where a point follows relative to
  • 0:40 - 0:43
    that decision boundary you can assign it a class label.
  • 0:43 - 0:46
    With a regression what we're trying to find is something we usually call
  • 0:46 - 0:47
    a best fit line.
  • 0:47 - 0:52
    Which is a line that fits the data rather than a boundary that describes it.
  • 0:52 - 0:54
    This will make a lot more sense in the next couple of videos.
  • 0:54 - 0:57
    The last thing I'll mention is how to evaluate.
  • 0:57 - 1:01
    When we were doing supervised classification we usually use the accuracy,
  • 1:01 - 1:05
    which is whether it got the class labels correct or not on your test set.
  • 1:05 - 1:09
    And for regression we'll talk about a couple different evaluation metrics.
  • 1:09 - 1:11
    One of which is called the sum of a squared error.
  • 1:11 - 1:13
    Another one is called r squared.
  • 1:13 - 1:17
    I'll tell you a lot more about both of these in the middle part of the lesson.
  • 1:17 - 1:19
    The main point I want you to take away from this is that,
  • 1:19 - 1:23
    while regression isn't exactly the same as supervised classification.
  • 1:23 - 1:27
    A lot of the things you already know about supervised classification have direct
  • 1:27 - 1:29
    analogs in regression.
  • 1:29 - 1:32
    So you should think of regression as a different type of supervised learning.
  • 1:32 - 1:35
    Not as a completely new topic that you now have to learn from scratch.
Title:
Comparing Classification and Regression - Intro to Machine Learning
Description:

more » « less
Video Language:
English
Team:
Udacity
Project:
ud120 - Intro to Machine Learning
Duration:
01:37

English subtitles

Revisions Compare revisions