Autoencoder

/ˈɔːtoʊɪnˌkoʊdər/

Autoencoder: A neural network trained to reconstruct its input, learning compressed representations in the process. Autoencoders consist of an encoder that compresses input to a latent representation and a decoder that reconstructs the original input. Used for dimensionality reduction, denoising, and feature learning.

In italiano: AutoencoderLegge III · Come una rete impara dai dati

Autoencoders consist of an encoder that compresses input to a latent representation and a decoder that reconstructs the original input. Used for dimensionality reduction, denoising, and feature learning.

Examples

  • Dimensionality reduction
  • Image denoising
  • Anomaly detection