YouTube

Got a YouTube account?

New: enable viewer-created translations and captions on your YouTube channel!

English subtitles

← Information Gain Calculation Part 9 - Intro to Machine Learning

Get Embed Code
5 Languages

Showing Revision 3 created 05/25/2016 by Udacity Robot.

  1. On this split, the information gain is actually zero.
  2. We don't learn anything by splitting the train,
  3. these particular training examples based on the bumpiness of the train.
  4. So this clearly is probably not where we want to start splitting our
  5. sample if we want to build a decision tree.