Skip to main content
PProfileMatch
← Path

Supervised Learning · Classification: Logistic Regression and Decision Trees Explained

0 XP
  1. 1 current stop: learning
  2. 2 upcoming
  3. 3 upcoming
  4. 4 upcoming
  5. 5 upcoming

Finish after stop 5

Stop 1 of 5 · Junction with a gentle S-bend

Trick to keep in mind+3 XP

Sigmoid bends any score into 0 to 1; a score of exactly 0 is the middle of the S.

Logistic regression computes an ordinary weighted score z, then passes it through 1 / (1 + e^-z). Very negative scores flatten toward 0 and very positive ones toward 1, and every real number is a valid input. To find the value at z = 0, remember what e raised to the power 0 equals.

Read it once, then a question tests whether the trick stuck.