Learning Notebook - David Rostcheck
Public View
learning_event details
Learning Event ID
Subject
Topic
Program
Length
Institution
Presenter
Format
Recorded Date
Completed Date
Notes
n autoencoder, autoassociator or Diabolo network is an artificial neural network used for learning efficient codings. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction. Recently, the autoencoder concept has become more widely used for learning generative models of data
Personal Notes
The basic idea is to use a neural network w/ same # of outputs as inputs to encode an input and then decode it. The loss function is the error between the correct representation and reconstructed representation.
Link
Review
Return to
main screen