Autoencoder

As explained in Outlier Detection in Python

An autoencoder is a neural network trained to encode an input into a representation and reconstruct the original input.

An autoencoder is a neural network trained to reproduce its input rather than predict a separate target. An encoder compresses each input into a smaller representation; a decoder uses that representation to reconstruct the original. For a table, an input is one row, with neurons corresponding to columns. For an image, the input can be its pixels. section 16.2.1

The narrowest layer is the embedding, bottleneck, or latent representation. Its values form a compact vector for each item. Reconstruction error measures how far the output is from the input; larger errors can indicate outliers. A two-dimensional latent space can make unusual points visible without making its axes readily interpretable. section 16.2.1 section 16.3.1

Figure 16.2 Example of an AE. The neural network learns to condense any input to as many elements as appear in the middle layer and then reconstruct the data to its original values.

The narrowing and widening layers show where compression happens and how the decoder attempts to recover the input. section 16.2.1

Tabular detection with PyOD

A KDD Cup example ordinal-encodes the table, then fits PyOD’s AutoEncoder and obtains outlier probabilities with predict_proba(X)[:, 1]. The listing sets epochs=5 and a random seed. Treat the resulting scores as detector output to assess, not proof that every flagged row is meaningful. section 16.2.1 section 16.2.2

Image reconstruction

An alibi-detect OutlierAE example reconstructs CIFAR10 images. A boat image is reconstructed closely; after random noise is added, its reconstruction error is high and it is flagged. Comparing the input and reconstruction helps inspect what drove the flag. section 16.4

Autoencoders are one reconstructive approach alongside variational autoencoders and other deep-learning detectors. They can add diversity to an ensemble, but tabular results are not generally stronger than established methods and training can be slower and harder to tune. A variational autoencoder also commonly uses reconstruction error for detection, but has a probabilistic latent representation and a generative objective. Another extension, AEGMM, jointly trains an autoencoder and Gaussian mixture model to assess both reconstruction and the learned representation. section 16.0 section 16.2.2 section 16.4

How Outlier Detection in Python covers it

How deep it goes

Explains encoder, bottleneck, decoder, and reconstruction, then demonstrates library detectors rather than deriving their training algorithms.

Examples

Demonstrates a PyOD detector on encoded KDD Cup records and an alibi-detect detector on clean and noise-perturbed CIFAR10 images.

What it assumes

Introduces encoder and decoder roles while assuming familiarity with tabular rows, image pixels, and basic neural networks.

What you can do after

Apply it via PyOD or alibi-detect to score candidate outliers and inspect image reconstructions.

How it connects

Connects embeddings and reconstruction error to variational autoencoders, Gaussian mixture models, and detector ensembles.

liveBookmanning.com

Read Outlier Detection in Python on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA neural network trained to reconstruct its input, typically by compressing it into a lower-dimensional latent representation and decoding it back.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA neural network model trained to compress inputs into a latent representation and reconstruct the original inputs from that representation.
• 

  liveBookmanning.com
  Data Without LabelsAn autoencoder is a neural-network model that learns to encode data into a lower-dimensional representation and reconstruct the original input from it.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksAn autoencoder is a neural network that learns to encode inputs into a representation and decode that representation to reconstruct the inputs.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA neural network that learns to compress inputs into a latent representation and reconstruct them, used here for digit-image generation and reconstruction.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionAn autoencoder is a neural network that encodes inputs into latent representations and decodes those representations to reconstruct the inputs.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentAn autoencoder is a neural network that learns to encode inputs into a lower-dimensional representation and reconstruct the original inputs.
• 

  liveBookmanning.com
  Financial AI in PracticeAn autoencoder is a neural network trained to reconstruct its input, typically by encoding it into a lower-dimensional representation and decoding it.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionAn autoencoder is a neural-network model that learns to encode inputs into representations and decode those representations back into approximations of the inputs.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA neural network trained to reconstruct its input, often by compressing and then decoding it, used here for denoising images.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionAn autoencoder is a neural network that learns to encode data into a compressed representation and reconstruct the original data from it.

Compare how 12 books explain 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.
• decoderhas part · A decoder is a component that maps encoded data or representations to decoded values, reconstructed data, or generated output.
• variational autoencoderincludes · A variational autoencoder is a generative neural network that learns a probabilistic latent representation of data and decodes samples from it to reconstruct or generate data.
• deep learningkind of · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
• neural networkkind of · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.
• Kerasuses · Keras is an open-source, high-level deep-learning API for building, training, evaluating, and deploying neural-network models.

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