AI engineering glossary · Deep learning core
What is autoencoder?
Autoencoder: A network trained to reproduce its own input by first compressing it into a small code and then reconstructing it. The bottleneck forces it to learn compact features, useful for denoising, anomaly detection and compression.
Autoencoder: an example
An autoencoder squeezing 784 pixel values into 32 numbers, then rebuilding the image, can flag unusual inputs by high reconstruction error.
Related terms
- Bottleneck
- Representation learning
- Loss function
More Deep learning core terms
- Autograd
- Backpropagation
- Backpropagation through time
- Backward pass
- Batch normalisation
- Batch renormalisation
- Batch size
- bfloat16
Where you learn it
Autoencoder is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.