What is the correct term used for this equation: w.x +b?

Course Q&A Machine Learning Specialization Supervised ML: Regression and Classification
1

Screenshot
Screenshot722×110 26.1 KB

w.x+b : what is it called?

2

Hi @RohitKamalV

In the context of the logistic equation or sigmoid function, the expression “w.x+b” represents the linear part of the equation, where “w” and “b” are the weights and bias, respectively, of the input variable “x”.

Please let me know if this answer your question

1 Like
3

Welcome to the community, @RohitKamalV!

In addition to @pastorsoto’s great answer:

It describes the exponent e.g. used in a logistic regression task; or let’s say:

  • x: the input of a sigmoid function,
  • b: the bias
  • w: the weight(s)
    where w and b are the model parameters that are learned within model training.

But dependent on your model you can also interpret this term as the cell body of a neuron within a larger neuron network (e.g. at a output layer of a binary classification problem):
Here also a visual interpretation possibility with a neuron where you can think of f as a sigmoid function, representing a nonlinear activation function of this layer:

Source: Choice of activation function - #8 by Christian_Simonis

Best regards
Christian

1 Like
4

It doesn’t have a specific name.