Data representation
A data representation is a form or encoding in which information is structured for storage, processing, transmission, or interpretation.
Deep Learning with R, Third Edition
A data representation is a particular encoding or view of data that can make a task easier to solve.
- How it is used
- Frames machine learning as the search for input transformations that make a task easier to solve.
- How deep it goes
- Defines representations with RGB, HSV, coordinates, and convolutional activations, then traces abstraction across network depth.
- Examples
- Uses RGB versus HSV images, classified coordinate points, cat-image activations, edge detectors, and higher-level visual features.
- What you can do after
- Evaluate/understand how alternative encodings and network layers preserve, discard, or emphasize information for a target.
Read how Deep Learning with R, Third Edition explains data representation →
Deep Learning with PyTorch, Second Edition
An internal data encoding produced or consumed by a model.
- How it is used
- Frames neural-network learning as transforming encoded inputs through task-specific intermediate features into useful outputs.
- How deep it goes
- Explains floating-point intermediate representations and a worked classifier, but defers handling image spatial structure.
- Examples
- Uses handwritten-digit features and a 32 × 32 image flattened for a two-class PyTorch classifier.
- What you can do after
- Apply it via PyTorch tensors and nn.Sequential to follow image values through hidden features to class outputs.
Read how Deep Learning with PyTorch, Second Edition explains data representation →
Machine Learning System Design
A learned or constructed encoding of data that captures information in a form suitable for input to a machine learning model.
- How it is used
- Supports ML inputs, transfer-learning baselines, shared data products, and similarity-oriented downstream systems.
- How deep it goes
- Defines representations as model inputs and gives reuse and storage patterns, while deferring detailed feature-engineering treatment.
- Examples
- Uses ImageNet image representations, linear classifiers, CLIP, SentenceTransformers, Qdrant, and Faiss as concrete artifacts.
- What you can do after
- Apply it via pretrained models to build shallow baselines, centralize embeddings, and retrieve similar items for downstream models.
Read how Machine Learning System Design explains data representation →
Modern C
A representation is the concrete encoding used to express a value inside a program or in an external file.
- How it is used
- Guides portable C programming by directing attention toward values rather than architecture- or type-dependent encodings.
- How deep it goes
- Defines representation and explains observable states and optimization, but does not detail particular binary encodings.
- Examples
- Uses decimal and Roman numerals, architecture-dependent encodings, and a floating-point computation optimized into fixed output.
- What you can do after
- Evaluate C behavior in terms of values and observable states without relying unnecessarily on concrete representations.
Related concepts
- neural network layerproduced by · A neural network layer is a computational stage or component that transforms input representations into outputs within a neural network.
- schemacontrasts with · A data schema is a formal specification of the structure, fields, types, relationships, and constraints of data.
- language modelproduced by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- neural networkproduced by · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.
- valuecontrasts with · A value is the content, quantity, information, or worth attributed to an entity, property, expression, or outcome.
- tokenimplemented by · A token is a discrete unit of text, such as a word, word fragment, character, or symbol, represented and processed as an element by a language model.
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.