Glossary term
Glossary term
Architecture
A system that learns to extract the most important information from the input. Autoencoders are a combination of an encoder and decoder. Autoencoders rely on the following two-step process:
The encoder maps the input to a (typically) lossy lower-dimensional (intermediate) format.
The decoder builds a lossy version of the original input by mapping the lower-dimensional format to the original higher-dimensional input format.
Autoencoders are trained end-to-end by having the decoder attempt to reconstruct the original input from the encoder's intermediate format as closely as possible. Because the intermediate format is smaller (lower-dimensional) than the original format, the autoencoder is forced to learn what information in the input is essential, and the output won't be perfectly identical to the input.
For example:
If the input data is a graphic, the non-exact copy would be similar to the original graphic, but somewhat modified. Perhaps the non-exact copy removes noise from the original graphic or fills in some missing pixels.
If the input data is text, an autoencoder would generate new text that mimics (but is not identical to) the original text.
See also variational autoencoders.
Created for this library
A fraud team trains an autoencoder on legitimate transactions and flags anything with high reconstruction error as suspicious.
A semiconductor manufacturer uses an autoencoder on wafer inspection images to compress them and detect anomalies in production.
A network operations team trains an autoencoder on normal traffic patterns to spot unusual flows that may indicate exfiltration.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License