From the course: Advanced Graph Neural Networks
Join today to access over 25,500 courses taught by industry experts.
A quick overview of autoencoders
From the course: Advanced Graph Neural Networks
A quick overview of autoencoders
- [Instructor] In the next predictive model that we'll build using graph neural networks, we are going to perform link prediction using graph auto encoders. Now, before we get to graph auto encoders, let's quickly understand what auto encoders are. We'll discuss auto encoders in general before we move on to graph auto encoders. Auto encoders are a type of neural network used for unsupervised learning that aims to learn efficient representations of input data, typically for the purpose of dimensionality reduction or feature extraction. Auto encoders generate latent space representations of the input data, which are then used to reconstruct the input. Auto encoders are made up of two parts, an encoder network, and a decoder network. The role of the encoder network is to compress the input data into lower dimensional latent space. Encoders typically comprise of several layers that progressively reduce the dimensionality of the input and thus capture the most relevant features of the…
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.