Deep Dive Into The Mind Of Autoencoders & Visualize Their Internals
Learn how Autoencoders work by writing one from scratch and plotting its internal state
What Is An Autoencoder?
An Autoencoder is a neural network that consists of:
Encoder — a neural network trained to encode a given high-dimensional item (such as image/ text/ audio) into a lower-dimensional space.
Decoder — a neural network trained to decode the lower-dimensional space to produce a high-dimensional item.
Keep reading with a 7-day free trial
Subscribe to Into AI to keep reading this post and get 7 days of free access to the full post archives.