From ed653e97e57fb7380b76a6aec82bef224551c1cc Mon Sep 17 00:00:00 2001
From: subahini <46754761+subahini@users.noreply.github.com>
Date: Mon, 23 Dec 2024 16:50:46 +0100
Subject: [PATCH] Update article.md

---
 2024/Art Of Knowing when to stop-(optimization)/article.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/2024/Art Of Knowing when to stop-(optimization)/article.md b/2024/Art Of Knowing when to stop-(optimization)/article.md
index ab19f927..21297b89 100644
--- a/2024/Art Of Knowing when to stop-(optimization)/article.md	
+++ b/2024/Art Of Knowing when to stop-(optimization)/article.md	
@@ -1,4 +1,5 @@
 # Art of Knowing When to Stop (Optimization)
+
 Think of optimization like perfecting a recipe: A baker named Sam kept adjusting his bread recipe to make it better. At first, small changes improved the bread, but when he added more changes the quality and taste stayed the same but the recipe got more complicated. He realized that the best version wasn’t necessarily the most complex one—it was the one that balanced simplicity and quality.
 
 The same idea applies to optimizing data and models. There’s a “sweet spot” between keeping things too basic and making them overly complex. True optimization means improving pipelines or models in ways that genuinely add value or maintain performance while avoiding unnecessary complications. The goal is to strike the right balance, just like Sam did with his bread