βNote, the orange line is βπ§β or π°β π±(π) + π above. It does not match the line in a linear regression model.β

I donβt get how βzβ is calculated and why itβs different from a linear regression model. Where do the βwβ and βbβ values come from to calculate βzβ in this example?

Are we using linear regression to find the values βwβ and βbβ, but each iteration of the algorithm performs the sigmoid function on βzβ?