Harris Quach
  • Home
  • About
  • Updates
  • Research
  • Software
  • Extended Posts

Activation Function

A function that follows the linear function in a neuron, to introduce nonlinearity.

If there existed no activation function, there would be no point in having individual neurons, as the entire network would become a single, big linear equation.

With Activation Function

\(w_2 \cdot \text{activation}(w_1 x + b_1) + b_2\)

Without Activation Function

\(w_2 \cdot (w_1 x + b_1) + b_2 = w_2 w_1 x + w_2 b_1 + b_2\)

Back to top

Harris Quach © 2024

  • Github

  • LinkedIn

  • Google Scholar

Version 2.2.1.5 | Feedback | Website made with Quarto