How to use auto encoder for unsupervised learning models?
How to use auto encoder for unsupervised learning models?
This recipe builds an autoencoder for compressing the number of features in the MNIST handwritten digits dataset.
For building an autoencoder, three components are used in this recipe :
- an encoding function,
- a decoding function,
- a loss function between the amount of information loss between the compressed representation of your data and the decompressed representation.
What is an Auto encoder ?
An auto encoder is used to encode features so that it takes up much less storage space but effectively represents the same data. It is a type of neural network that learns efficient data codings in an unsupervised way. The aim of an autoencoder is to learn a representation for a dataset, for dimensionality reduction, by ignoring signal "noise".
What is Unsupervised learning model ?
Unsupervised machine learning models infer patterns from a dataset without reference to known, or labeled, outcomes. Unlike supervised machine learning, unsupervised machine learning methods cannot be directly applied to a problem because you have no idea what the values for the output data might be, making it impossible for you to train the algorithm the way you normally would. Unsupervised learning can instead be used for discovering the underlying structure of the data.
