autoencoder
Sign in to savethumb|upright=1.15|A schema of an autoencoder. An autoencoder has two main parts: an encoder that maps the message to a code, and a decoder that reconstructs the message from the code.
Article
28 sectionsContents
- Mathematical principles
- Definition
- Training an autoencoder
- Interpretation
- Variations
- Variational autoencoder (VAE)
- Sparse autoencoder (SAE)
- Denoising autoencoder (DAE)
- Contractive autoencoder (CAE)
- Minimum description length autoencoder (MDL-AE)
- Concrete autoencoder (CAE)
- Advantages of depth
- Training
- History
- Applications
- Dimensionality reduction
- Principal component analysis
- Information retrieval
- Autoencoder hippocampus network
- Anomaly detection
- Image processing
- Drug discovery
- Popularity prediction
- Machine translation
- Communication Systems
- See also
- Further reading
- References
thumb|upright=1.15|A schema of an autoencoder. An autoencoder has two main parts: an encoder that maps the message to a code, and a decoder that reconstructs the message from the code.
An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction, to generate lower-dimensional embeddings for subsequent use by other machine learning algorithms.