Representation learning
Representation learning is the process by which a machine-learning model learns useful representations or features of data from examples.
Timeless Algorithms, The Foundational Ideas
Representation learning transforms raw data into representations that retain information useful for downstream tasks.
- How it is used
- Explains how learned transformations make raw data more useful for downstream processing and prediction.
- How deep it goes
- Explains information-preserving compression and geometric class separation, without specifying an implementation procedure.
- Examples
- Uses image compression and a circles-versus-squares classification problem to illustrate learned representations.
- What you can do after
- Evaluate and understand how representations can reduce redundancy or simplify classification, and why training-set separation alone does not ensure generalization.
Read how Timeless Algorithms, The Foundational Ideas explains representation learning →
Build AI Drug Discovery Pipelines
Representation learning is a technique in which a model learns useful encoded features from raw data.
- How it is used
- Uses unlabeled data to emphasize useful signal and reduce distracting noise in raw data.
- How deep it goes
- Defines the signal-noise objective and relates it to dimensionality reduction and compression without detailing algorithms or implementation.
Read how Build AI Drug Discovery Pipelines explains representation learning →
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
Representation learning is the automatic discovery of useful data representations from input data.
- How it is used
- Frames deep learning as an approach that discovers task-relevant data representations internally.
- How deep it goes
- Explains nonlinear interactions, compact formats, and hierarchical representations without detailing specific network architectures.
- Examples
- Uses hierarchical transformations from basic features to complex abstract patterns and compact task-specific formats.
- What you can do after
- Evaluate when learned representations may replace manual feature engineering and when tabular data still requires deliberate feature work.
Outlier Detection in Python
Representation learning is the process of learning useful numerical representations of objects from data.
- How it is used
- Creates reusable numerical inputs when sufficient hand-labeled data is impractical.
- How deep it goes
- Explains embedding extraction and reuse, while stopping short of detailed network architecture or training mathematics.
- Examples
- Uses transformed images, image rotations, and tabulated mug-image embeddings as concrete examples.
- What you can do after
- Apply learned embeddings as inputs to downstream predictive models with less labeled data.
Read how Outlier Detection in Python explains representation learning →
Data Without Labels
Feature learning is the automated discovery of useful data representations or features by a model during training.
- How it is used
- Automates discovery of useful representations for feature detection, especially in image, text, audio, and video datasets.
- How deep it goes
- Defines supervised and unsupervised approaches, then details autoencoder components, training choices, applications, and limitations.
- Examples
- Uses autoencoders for dimensionality reduction, anomaly detection, data compression, and synthetic-data generation.
- What you can do after
- Apply it via neural networks or autoencoders to discover representations without manual feature engineering.
Read how Data Without Labels explains representation learning →
Also covered in
- Knowledge Graphs and LLMs in Action
- Sutskever's List
- Evolutionary Deep Learning: Genetic algorithms and neural networks
- LLM Evaluation and Alignment, The Foundational IdeasIn early access (MEAP)
- Deep Learning with R, Third Edition
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- deep learningDeep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
- machine learningMachine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- convolutional layerA convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
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 composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
- data representationproduces · A data representation is a form or encoding that structures information for interpretation, processing, storage, or exchange.
- language modelincludes · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- feature engineeringcontrasts with · Feature engineering is the creation, transformation, or selection of input features from data to provide useful representations for analysis or modeling.
Questions about representation learning
What is representation learning?
Representation learning is the process by which a machine-learning model learns useful representations or features of data from examples.
Which Manning books explain representation learning?
Timeless Algorithms, The Foundational Ideas, Build AI Drug Discovery Pipelines, Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI, Outlier Detection in Python and Data Without Labels.
What should I know before learning representation learning?
Manning books that teach representation learning usually introduce language model, deep learning, machine learning and convolutional layer first.
What is the difference between representation learning and handcrafted descriptor?
Representation learning is the process by which a machine-learning model learns useful representations or features of data from examples. A handcrafted descriptor is a human-designed representation of measurable input properties, specified using domain knowledge rather than learned directly from data.
What kinds of representation learning are there?
Kinds of representation learning include language model.
What is representation learning also called?
Representation learning is also called feature learning.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.




