Graph Networks are extremely useful tools to help understand the graph data that’s all around us. In this episode, I’m going to explain what some of the latest advancements in graph networks are and how you can leverage them to build your own graph network in a few lines of Python code. This space has matured so much that there is never a single library to discuss, there are always multiple competing options (which is a great thing). We’ll be weighing the pros and cons of the Deep Graph, Graph Nets, and PyTorch Geometric library as well. I’m particularly interested in Graph Networks because of how well suited they are for interpreting the most complex biochemical factory that we know of – the human body. Enjoy!
TWITTER:
WEBSITE:
INSTAGRAM:
FACEBOOK:
Coding Challenge Submission link ( Due Jan 26, 2019 at 12 PM PST):
This is the example code from the video by the Deep Graph team, originally the toy dataset was the ‘karate club’ one, but i wanted to demo something more meaningful so i changed it to a toy ‘protein network’:
Type the code into Colab if you don’t want to install it locally:
Simple Neural Network by Milo Harper:
Subscribe for more educational videos!
The Deep Graph Library:
The Graph Nets Library:
PyTorch Geometric Library:
The Hyperfoods paper:
Read any research paper for free by typing it into this:
Are you a total beginner to machine learning? Watch this:
Learn Python:
Learn PyTorch:
Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams!
Signup for my newsletter for exciting updates in the field of AI:
Credits:
The I’M HIP-HOP Youtube channel for the Drake God’s Plan beat
The Deep Graph team
Milo Harper
And please support me on Patreon:
