From the course: Learning Graph Neural Networks
Join today to access over 24,400 courses taught by industry experts.
Exercise: Setting up a DNN as a baseline model
From the course: Learning Graph Neural Networks
Exercise: Setting up a DNN as a baseline model
- [Instructor] Our objective in this machine learning problem is to perform node classification. You want to classify the research papers into whether they're about agents, machine learning, AI, or any of the six classes or categories that we have. Before we use graph convolution networks, the first thing that we'll do is set up a simple dense neural network, a multi-layer perceptron to classify the nodes into categories. Now, in theory, we should be able to infer the category of a document solely based on its contents. That is its bag of words feature representation without taking any relationship between nodes into account. If you remember, we have a feature vector associated with each node representing the presence or absence of words from a predefined dictionary. In the research paper represented by that node, I'll now set up a simple dense neural network to perform node classification based only on the node features without taking the structure of the graph into account, without…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
