An encoder squeezes the input through a narrow bottleneck and a decoder rebuilds it. Because the bottleneck cannot carry everything, the network must learn what matters.
Useful for denoising, for anomaly detection — anything reconstructed badly is unlike the training data — and, in its variational form, as a generative model in its own right.
JOIN NOW
Begin the first module
It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.
Join any time · Build AI skills at your pace