How deeply does Outlier Detection in Python cover representation learning?

Explains embedding extraction and reuse, while stopping short of detailed network architecture or training mathematics.

Representation learning

As explained in Outlier Detection in Python

Representation learning is the process of learning useful numerical representations of objects from data.

Representation learning finds useful numerical representations of objects from data. In deep learning, these representations are often embeddings: values from a trained network's second-last layer, selected because they preserve information useful for prediction. section 16.5.1

A practical workflow is:

Train a neural network on a prediction or self-supervised pretext task. section 16.5.1
Extract embeddings from the second-last layer rather than using the final prediction. section 16.5.1
Use the embeddings as input to classifiers, regressors, or other predictive models. section 16.5.1

Learning from image transformations

A network can learn to predict whether an image was cropped, discolored, stretched, or rotated. Its second-last-layer values then represent image characteristics for later prediction tasks. section 16.5.1

How Outlier Detection in Python covers it

liveBook manning.com

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

Also explained in

liveBook manning.com

Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIRepresentation learning is the automatic discovery of useful data representations from input data.
liveBook manning.com

Data Without LabelsFeature learning is the automated discovery of useful data representations or features by a model during training.

Compare how 3 books explain representation learning →

Related concepts

deep learningused by · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
neural networkuses · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.
data representationproduces · A data representation is a form or encoding in which information is structured for storage, processing, transmission, or interpretation.
language modelincludes · A language model is a computational model that represents patterns in linguistic tokens to estimate their probabilities and predict or generate sequences of them.
feature engineeringcontrasts with · Feature engineering is the creation, transformation, or selection of input features from data to provide useful representations for analysis or modeling.

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.