Harpreet Sahota 🥑
Harpreet Sahota 🥑

@DataScienceHarp

11 Tweets 2 reads Nov 07, 2022
Python is the most important language to learn for deep learning.
I learned it all wrong when I first started.
Here’s the path I’d take if I was to do it all over again…
🧵
1) Python principles
This is where I would go to first. It teaches the absolute fundamentals and basic principles of Python.
Lessons teaching it from the ground up + challenges that will help prep you for more difficult things.
Register for free: pythonprinciples.com
2) Tech World w/ Nana
@Njuchi_’s tutorial is amazing. It’ll teach you the basics and give you better intuition than most courses out there.
Five hours well spent, should take you a week to stumble and struggle and learn through it
m.youtube.com
3) Visual tutor
You’ll inevitability run into code where you can’t yet reason through what it’s doing.
Visual tutor helps you visualize the execution of your code, helping you build a better understanding of what’s going on under the hood
#mode=edit" target="_blank" rel="noopener" onclick="event.stopPropagation()">pythontutor.com
4) Learn numpy
Read this blog to get a better understanding of numpy
betterprogramming.pub
Then go through all the resources on the official numpy site
numpy.org
5) numpy zero to hero
Go through this video and code along with it.
It’s 4.5 hours long, should take you a week to grind though.
m.youtube.com
6) Code a neural network from scratch using only numpy
This tutorial will walk you through it
You’ll understand the mechanics of a neural network and gain appreciation for what libraries like tensorflow and PyTorch are behind the scenes
mlfromscratch.com
7) Learn PyTorch
Deep learning with PyTorch is an amazing book.
Here is it: isip.piconepress.com
That should be enough to get you started.
From here it’s repetition and practice.
You can join my open community of mid to advanced practitioners who will help you along the way.
deeplearningdaily.community
Be sure to follow me @DataScienceHarp for more content like this and hit the 🔔 so you don’t miss out.

Loading suggestions...