Back to Blog
Deep Dive

Latent Spaces

How neural networks learn to compress data into a low-dimensional code and reconstruct it: the encoder-decoder pair, the link to PCA, denoising and sparse variants, and the manifold that emerges from reconstruction alone.

6 articles
~72 min total
Machine LearningRepresentation LearningMetric LearningAutoencodersUnsupervised LearningVAE

Articles in this Series(showing 0 of 6)

No articles match your search criteria.