Concept - Sigmoid Function

Also “logistic function” (s.257).

$\sigma (t)=\frac{1}{1+e^{-t}}=\frac{e^t}{1+e^t}$

• Input $t\in (-\infty ,+\infty )$; output $\sigma (t)\in (0,1)$, a probabilistic score.
• S-shaped; $\sigma (0)=0.5$; tends to 0 and 1 at the extremes.
• Plugging $t=wx+b$ turns linear regression into Concept - Logistic Regression (s.258).

Related

Concept - Logistic Regression, Concept - Linear Regression

Sources: 03 Text Classification - Chunk 09 (s.241-270)