Explore Courses Blog Tutorials Interview Questions
0 votes
in AI and Deep Learning by (50.2k points)

It seems there is a bit of confusion between activation and transfer function. From Wikipedia ANN:

enter image description here

It seems that the transfer function calculates the net while the activation functions the output of the neuron. But on Matlab documentation of an activation function I quote:

Stalin(N, FP) is a neural transfer function. Transfer functions calculate a layer's output from its net input.

So who is right? And can you use the term activation function or transfer function interchangeably?

1 Answer

0 votes
by (108k points)

The activation function is the one who decides whether a neuron should be activated or not by calculating a weighted sum and further adding bias with it. The purpose of the activation function is to introduce non-linearity into the output of a neuron.

Transfer function comes from the name transformation and is used for transformation purposes i.e. from input nodes to the output of a neuron. On the other hand, activation function checks for the output if it meets a certain threshold and either outputs zero or one.

Become Master of AI Neural network by going through this what is Neural network?

Welcome to Intellipaat Community. Get your technical queries answered by top developers!

30.5k questions

32.6k answers


108k users

Browse Categories