Activation functions

We now know that an ANN is created by stacking individual computing units called perceptrons. We have also seen how a perceptron works and have summarized it as Output 1, IF  .

That is, it either outputs a 1 or a 0 depending on the values of the weight, w, and bias, b.

Let's look at the following diagram to understand why there is a problem with just outputting either a 1 or a 0. The following is a diagram of a simple perceptron with just a single input, x:

For simplicity, let's call  , where the following applies:

  • w is ...

Get Mobile Artificial Intelligence Projects now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.