Return to Video

Dimensions when Learning From Text - Intro to Machine Learning

  • 0:01 - 0:04
    So one of the most exciting developments in machine learning is
  • 0:04 - 0:07
    learning from text.
  • 0:07 - 0:12
    A lot of the online data is actually text data, the web, emails and so on.
  • 0:12 - 0:14
    And companies like Google, Yahoo!,
  • 0:14 - 0:18
    and many others are really built on the idea that you
  • 0:18 - 0:20
    can use machine learning and apply it to text.
  • 0:20 - 0:23
    So if you want to build the next Google, listen up.
  • 0:23 - 0:27
    The fundamental question in learning from text has to do
  • 0:27 - 0:28
    with what's the input feature.
  • 0:28 - 0:31
    And I'm going to give an example and ask you a question.
  • 0:31 - 0:35
    Suppose you have two strings, two kind of sentences.
  • 0:35 - 0:40
    One is called nice day, and one is called a very nice day.
  • 0:40 - 0:44
    And suppose for whatever reason, one is a positive example.
  • 0:44 - 0:48
    And one of the negative examples is indicated by this X over here and
  • 0:48 - 0:49
    this circle.
  • 0:50 - 0:52
    And maybe if many of those, and
  • 0:52 - 0:55
    you want to toss them into your favorite learning algorithm like the support
  • 0:55 - 0:58
    vector machine to produce either output label.
  • 0:58 - 1:03
    What do you think is the best input dimension for the support vector machine?
  • 1:03 - 1:09
    Give you a few choices, one, two, three, four or hard to tell.
  • 1:09 - 1:11
    Give it a best shot.
Title:
Dimensions when Learning From Text - Intro to Machine Learning
Description:

more » « less
Video Language:
English
Team:
Udacity
Project:
ud120 - Intro to Machine Learning
Duration:
01:12

English subtitles

Revisions Compare revisions