Variational autoencoder

As explained in Generative AI in Action

A variational autoencoder is a generative neural model that encodes data into a probabilistic latent representation and decodes samples from that representation into reconstructed or newly generated data.

A variational autoencoder (VAE) generates new data points that resemble its input data while allowing variation. For images, that can mean creating faces or designs similar to those it has learned, rather than exact copies. VAEs can also support anomaly detection and recommendation systems. section 4.1

A VAE has two neural networks. An encoder maps an image to a lower-dimensional latent space that captures essential features. Instead of choosing only one latent point, it represents a distribution described by a mean and variance. A decoder samples from that distribution and reconstructs an image. Different samples allow different, related outputs. section 4.1.1

Figure 4.4 Variational autoencoder architecture

Follow the input through the encoder, latent representation, and decoder to see where sampling enters the generation process. section 4.1.1

Useful image tasks include:

• Generating images that share features with training images, such as faces, fashion designs, or art. section 4.1.1
• Reconstructing missing or corrupted image regions, including in medical images or old photographs. section 4.1.1
• Transferring stylistic elements between images or manipulating image features. section 4.1.1

Choose the architecture to fit the task. VAEs are suited to producing varied data similar to the original, including relatively simple images; GANs target greater realism in complex, diverse images, while diffusion models target high-quality modeling of complex data when generation speed is less important. A VAE can also be a component within a diffusion system. For deployed image generation, consider image quality, speed, computing resources, training data, and questions of ownership and authenticity. section 4.1 section 4.1.4

How Generative AI in Action covers it

How deep it goes

Explains encoder–decoder flow and sampling through mean and variance without deriving training mathematics or providing implementation code.

Examples

Uses generated faces, fashion designs, art, medical-image repair, and photograph restoration as examples.

What it assumes

Introduces mean, variance, and normal-distribution sampling in plain language while treating neural networks as familiar components.

What you can do after

Evaluate/understand it as an option for generating image variations or reconstructing images, while weighing task and deployment requirements.

How it connects

Relates VAEs to latent spaces, image inpainting, style transfer, GANs, and diffusion models.

liveBookmanning.com

Read Generative AI in Action on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A variational autoencoder is a generative neural model that encodes data into a lower-dimensional probabilistic latent representation and decodes that representation into reconstructed or generated data.
• 

  liveBookmanning.com
  Causal AIA variational autoencoder is a generative neural-network model that combines an encoder-defined approximating distribution with a decoder-defined generative distribution over observed data and latent variables.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA generative model that learns an encoder-decoder latent-variable representation so it can reconstruct inputs and sample new outputs from latent space.
• 

  liveBookmanning.com
  Outlier Detection in PythonA variational autoencoder is a generative neural-network model that learns a probabilistic latent representation and reconstructs or generates observations from it.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningAn autoencoder that models the latent space probabilistically and is trained with regularizing constraints.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA generative latent-variable model that learns an encoder-decoder structure and a probabilistic latent space for reconstructing and sampling data.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksA variational autoencoder is a neural network that encodes inputs as probability distributions, samples from those distributions, and decodes the samples to reconstruct or generate data.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA variational autoencoder is a probabilistic autoencoder whose encoder represents inputs as parameters of a latent probability distribution and whose decoder reconstructs or generates data from sampled latent points.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA variational autoencoder is a generative neural network that learns an approximate latent-variable posterior and reconstructs observations from sampled latent representations.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA variational autoencoder is a neural network architecture that encodes data into a probabilistic latent space and decodes latent representations to reconstruct or generate data.
• 

  liveBookmanning.com
  Data Without LabelsA variational autoencoder is a neural-network generative model that learns a probabilistic latent representation and reconstructs data from sampled latent variables.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionA variational autoencoder is a probabilistic autoencoder that learns a parameterized latent-variable distribution and decodes samples from it to reconstruct or generate data.

Compare how 13 books explain variational autoencoder →

Related concepts

• encoderhas part · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.
• autoencoderkind of · An autoencoder is a neural network that encodes input data into an internal representation and decodes it to reconstruct the input or an approximation.
• decodehas part · Decoding is the process of transforming an encoded or internal representation into an interpretable or target-form output.
• generationkind of · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
• reconstruction lossuses · Reconstruction loss is a measure of the discrepancy between an input or observation and the output a model reconstructs from it or its representation.
• image generationuses · Image generation is the computational creation of new images from learned models, input data, or specified conditions.

This explainer was generated by Manning's knowledge graph from the text of Generative AI in Action. The section links point to the parts of the book it draws on.