> For the complete documentation index, see [llms.txt](https://techacademy.gitbook.io/ai-track-wise24_25/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://techacademy.gitbook.io/ai-track-wise24_25/section-3-neural-networks/exercise-the-softmax-function.md).

# Exercise - The Softmax Function

A special activation function used in classification networks is the softmax activation function. This function turns any input function into a probability function.

{% file src="/files/Nr5rlxto3rsmbui96Zdl" %}

The softmax function is often used to map the output of transformation layers to a probability function. In this notebook you will implement this function in Python and have a look at its characteristics.

<figure><img src="https://content.gitbook.com/content/0yllaCQ5tDTzssP05wwd/blobs/G3awFOWLf7HxuNxLwJjr/softmax.png" alt=""><figcaption></figcaption></figure>