This is a comprehensive guide to understanding Gradient Descent. We'll cover the entire process from scratch, providing an end-to-end view. Plus, witness a visual representation with a Gradient Descent animation.
Code used: https://github.com/campusx-official/100-days-of-machine-learning/tree/main/day51-gradient-descent
Google Tool used: https://developers.google.com/machine-learning/crash-course/fitter/graph
============================
Do you want to learn from me?
Check my affordable mentorship program at : https://learnwith.campusx.in/s/store
============================
📱 Grow with us:
CampusX' LinkedIn: https://www.linkedin.com/company/campusx-official
CampusX on Instagram for daily tips: https://www.instagram.com/campusx.official
My LinkedIn: https://www.linkedin.com/in/nitish-singh-03412789
Discord: https://discord.gg/PsWu8R87Z8
E-mail us at
[email protected]
⌚Time Stamps⌚
00:00 - Intro
01:15 - Summary of Gradient Descent
04:10 - What is gradient descent?
05:22 - Plan of attack
07:25 - Intuition for GD
28:45 - Mathematical Formulation of Gradient Descent
36:11 - Code Demo
47:41 - Creating our own class and methods
57:16 - Vizualizing our class
01:05:05 - Effect of Learning Rate
01:07:33 - Universality of GD
01:10:23 - Performing Gradient Descent by adding 'm'
01:14:15 - Vizualisation
01:23:48 - Code Demo and Vizualization
01:44:35 - Effect of Learning rate
01:49:25 - Effects of Loss Function
01:55:12 - Effect of Data