What is Variational Autoencoder (VAE)?
A Variational Autoencoder (VAE) is a type of generative model in machine learning that combines elements of both autoencoders and probabilistic modeling. VAEs are used for unsupervised learning tasks, particularly in generating new data samples that resemble the training data.At its core, a VAE consists of an encoder and a decoder. The encoder takes an input data point and maps it to a latent space representation. This latent space is a lower-dimensional representation that captures the key features and variations in the data. The encoder network learns to encode the input data into the latent space by applying various transformations and reducing the dimensionality.Related terms
Not to be confused with:
Back to glossary
