Skip to content

Tarik Billa

  • Web Development
    • html
    • vue.js
    • laravel
    • css
    • javascript
    • jquery
    • node.js
    • php
    • asp.net
  • Programming
    • python
    • java
    • c
    • c++
    • c#
  • git
  • android

relu

ReLU derivative in backpropagation

April 7, 2024 by Tarik

since ReLU doesn’t have a derivative. No, ReLU has derivative. I assumed you are using ReLU function f(x)=max(0,x). It means if x<=0 then f(x)=0, else f(x)=x. In the first case, when x<0 so the derivative of f(x) with respect to x gives result f'(x)=0. In the second case, it’s clear to compute f'(x)=1.

Categories neural-network Tags backpropagation, neural-network, relu, sigmoid Leave a comment

Tarik Billa

Software Engineer
tarikbilla@gmail.com
+8801884414000
  • Reuse a hash in YAMLApril 17, 2024
  • Dockerfile: how to redirect the output of a RUN command to a variable?April 16, 2024
  • How to cd to a directory with spaces in the directory name?April 16, 2024
  • Maximum MIME type length when storing the type in a databaseApril 16, 2024
  • What is the difference between Unit, Integration, Regression and Acceptance Testing?April 16, 2024
© 2026 Tarik Billa