I'm a beginner in ML, and have a question on back propagation cost function.

I'm reading the material on this link. In the below screen, since $a$ is the neuron's output, then why $a = \sigma(z)$ instead of $a = z$ directly?

What does $\sigma$ mean exactly here?

enter image description here

  • 2
    $\begingroup$ Sigma is called an activation function. Its used to add nonlinearity to the network. $\endgroup$ – Matthew Drury Sep 3 '17 at 13:04
  • $\begingroup$ @MatthewDrury Thanks a lot Matthew! Yea, I missed the part for activation function. $\endgroup$ – Bon Sep 3 '17 at 13:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.