No account yet ?

transformer-cnn-emotion-recognition

  Copyright (c) 2019 Rana Hanocka

GitHub

An autoencoder is a type of artificial neural network used to learn efficient encodings of unlabeled data.

The coding is validated and refined by attempting to regenerate the input from the coding.

The autoencoder learns a representation for a set of data, usually for dimensionality reduction, by training the network to ignore insignificant data.

Variants exist, aiming to force learned representations to assume useful properties.

Examples are regularized autoencoders, which are efficient in learning representations for later classification tasks, and variational autoencoders, with applications as generative models.

Automatic encoders are applied to many problems, including face recognition, feature detection, anomaly detection, and word meaning acquisition.

Autoencoders are also generative models that can randomly generate new data similar to the input data.