---
title: "Discussion on \"ML Experiment Log: Squaring as activation layer\" | Hashnode"
description: "Discussion on \"ML Experiment Log: Squaring as activation layer\". The purpose of an activation layer is to add some non-linearity to the network.  This allows expressing much more complex tasks with our networks.\nBut why do we generally use functions that have a low/zero less than zero component and a nearly 1 comp..."
url: "https://hashnode.com/posts/ml-experiment-log-squaring-as-activation-layer/63416a5e4d9af734c1172012"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [ML Experiment Log: Squaring as activation layer](https://www.jimmiebtlr.com/ml-experiment-log-squaring-as-activation-layer?utm_source=hashnode&utm_medium=feed)

The purpose of an activation layer is to add some non-linearity to the network. This allows expressing much more complex tasks with our networks. But why do we generally use functions that have a low/zero less than zero component and a nearly 1 comp...

Oct 8, 2022 · 4 min read · jimmiebtlr.com  
Read the article

-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#research](https://hashnode.com/tag/research)

## Written by

[Jimmie Butler](https://hashnode.com/@jimmie)

@jimmie · Lisbon,Portugal

  
[View profile](https://hashnode.com/@jimmie)

Freelance Developer

I'm a freelance full stack developer with 10 years experience. Generative design with machine learning is something I'm interested in and researching in my free time.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
