Explain one-hot encoding in episode 2?

carpentries-incubator / deep-learning-intro

Learn Deep Learning with Python

https://carpentries-incubator.github.io/deep-learning-intro/

Other

30 stars 36 forks source link

Explain one-hot encoding in episode 2? #488

Closed svenvanderburg closed 2 months ago

svenvanderburg commented 3 months ago

From @mike-ivs comments:

a question that was raised a few times when we delivered this lesson in past workshops was "why do we use 3 columns of 0/1 instead of just one column 0/1/2 for the 3 labels?" i.e. why one-hot instead of label encoding (without knowing the names)
It might be worth elaborating on why we want to "make things more complex" via one-hot encoding i.e. discuss the "ranking issue" of label encoding.
This may slow things down due to extra detail, but this was a point where we risked our learners falling behind without a proper explanation.

svenvanderburg commented 3 months ago

@mike-ivs thanks for your comment!

My thoughts:

We assume basic machine learning knowledge as a prerequisite, so not sure if we should go into details here.
Of course sometimes leaners ask this question. But in this case I would say it is one of the 1000 possible questions learners might ask and I am not sure if we should tackle all of them in the lesson content. I think in this case the instructor has enough information to answer the question.

mike-ivs commented 3 months ago

Fair points! Probably more a sign of our own workshop delivery than the lesson itself, feel free to close this change :) (we've delivered this DL lesson the day after another ML lesson which doesn't cover encoding)

svenvanderburg commented 2 months ago

Cool! I'll close then.