Tensor
A tensor is a multidimensional numerical array whose values are arranged along indexed dimensions and can be manipulated through mathematical computation.
Deep Learning with R, Third Edition
A JAX array is JAX's numerical array object representing values on which transformed and accelerated computations can operate.
- How it is used
- Introduces tensors as containers for neural-network data and learned weights.
- How deep it goes
- Explains rank, shape, dtype, slicing, and common data layouts through runnable examples rather than formal derivations.
- Examples
- Uses MNIST image arrays, JAX array creation, and PyTorch tensor operations as concrete examples.
- What you can do after
- Apply it via R and NumPy to inspect, slice, and preprocess tensors for a neural network.
Read how Deep Learning with R, Third Edition explains tensor →
Natural Language Processing in Action, Second Edition
A tensor is a multidimensional numerical array used to represent and transform structured data in machine-learning computations.
- How it is used
- Uses tensors to carry text features, model weights, and predictions through neural-network computations.
- How deep it goes
- Works through tensor conversion, dimensions, and CNN layer shapes; does not explain tensor storage internals.
- Examples
- Uses part-of-speech pattern matching and a CNN text classifier to demonstrate tensor construction and shape changes.
- What you can do after
- Apply it via PyTorch to convert tabular data, prepare convolution inputs, and inspect output shapes.
Read how Natural Language Processing in Action, Second Edition explains tensor →
Learn Generative AI with PyTorch
A multidimensional numerical array used in PyTorch to represent model inputs, outputs, and intermediate values.
- How it is used
- Uses tensors to prepare and hold numerical inputs for deep learning models.
- How deep it goes
- Works through creation, data types, indexing, reshaping, concatenation, and dimension-specific reductions.
- Examples
- Uses presidential heights, Fashion MNIST images, and exponential-curve training data to demonstrate tensor operations.
- What you can do after
- Apply tensor operations via PyTorch to create, inspect, reshape, index, and summarize numerical data.
Build AI Drug Discovery Pipelines
A tensor is a multidimensional numerical array that stores data and supports operations for machine-learning computation.
- How it is used
- Uses tensors to represent neural-network inputs, outputs, and parameters in a drug-discovery workflow.
- How deep it goes
- Defines tensors and demonstrates creation, inspection, conversion, indexing, reshaping, concatenation, and mathematical operations.
- Examples
- Demonstrates two-dimensional arrays and converts molecular fingerprints and kinase activities into tensors.
- What you can do after
- Apply it via PyTorch to create, inspect, convert, and manipulate tensors for a neural-network dataset.
Read how Build AI Drug Discovery Pipelines explains tensor →
Grokking AI Algorithms, Second Edition
A tensor is a multidimensional numerical array used to represent data and intermediate computations in machine-learning models.
- How it is used
- Uses tensors to represent neural-network inputs, weights, outputs, and image feature maps for layer-wide computation.
- How deep it goes
- Defines tensors by dimension and illustrates image shapes and decoder concatenation, while deferring the details of tensor algebra.
- Examples
- Illustrates scalars, vectors, image batches, an 8×8 color image, and concatenated U-Net feature maps.
- What you can do after
- Supports evaluating and understanding tensor shapes and their role in neural-network computation.
Read how Grokking AI Algorithms, Second Edition explains tensor →
Build a Text-to-Image Generator (from Scratch)
A tensor is a multidimensional numerical array used to represent data and intermediate computations in a neural network.
- How it is used
- Represents images, token sequences, embeddings, and intermediate neural-network computations for training and inference.
- How deep it goes
- Explains shapes, values, dtypes, padding, batching, and device placement while deferring detailed attention calculations.
- Examples
- Uses normalized image batches, a padded 2 × 64 prompt tensor, and a 4 × 256 sentence-embedding tensor.
- What you can do after
- Apply it via PyTorch to convert, shape, batch, normalize, pad, and place model inputs on CPU or CUDA.
Read how Build a Text-to-Image Generator (from Scratch) explains tensor →
GPU Programming with Triton
A tensor is a multidimensional array used to represent and manipulate structured data.
- How it is used
- Represents structured numerical data for blocked GPU computations in deep learning and scientific workloads.
- How deep it goes
- Explains tile execution, matrix memory layout, and local reductions, while noting that grid-wide reductions require extra orchestration.
- Examples
- Uses matrix multiplication and tile-local sum, maximum, and custom reductions as examples.
- What you can do after
- Understand how Triton maps tensor tiles to GPU work and why matrix layout and reduction scope matter.
Deep Learning with Python, Third Edition
A tensor with three axes, used here for an image or feature-map representation with height, width, and depth.
- How it is used
- Represents images and convolutional feature maps through height, width, and depth axes.
- How deep it goes
- Defines rank-3 dimensions and channels, then demonstrates convolutional transformation without detailing tensor operations beyond feature extraction.
- Examples
- Uses RGB images, black-and-white MNIST inputs, and a (28, 28, 1) to (26, 26, 64) transformation.
- What you can do after
- Evaluate/understand how spatial axes and channels encode images and learned visual patterns.
Read how Deep Learning with Python, Third Edition explains tensor →
Geometry for Programmers
A multidimensional array is an indexed data structure containing values arranged along two or more dimensions.
- How it is used
- Generalizes vectors and matrices when describing multidimensional data structures with defined operations.
- How deep it goes
- Defines tensor algebra and connects it to vector and matrix operations without detailing higher-dimensional tensor operations.
- Examples
- Uses a nested 2D array and a 3×3 inertia tensor to illustrate tensor representations.
- What you can do after
- Understand tensors as structured arrays and recognize vectors and matrices as tensor cases.
Retrieval Augmented Generation, The Foundational Ideas
A tensor is a multidimensional numerical array used to represent data and intermediate computations in machine-learning models.
- How it is used
- Represents independently encoded passages and exposes them as decoder inputs for joint answer synthesis.
- How deep it goes
- Explains tensor shape and reshape-based fusion, but stops short of general tensor operations or numerical implementation details.
- Examples
- Uses N question–title–passage sequences and an [N, sequence_length, hidden] encoder output.
- What you can do after
- Evaluate/understand how FiD reshapes encoder tensors before decoder cross-attention.
Read how Retrieval Augmented Generation, The Foundational Ideas explains tensor →
Also covered in
- Server-Side WebAssembly
- Deep Learning with JAX
- AI-Powered Search
- .NET in Action, Second Edition
- Sutskever's List
- Modern C, Third Edition
- Go in Action, Second Edition
- Bayesian Optimization in Action
- Evolutionary Deep Learning: Genetic algorithms and neural networks
- Julia as a Second Language
- Grokking Data Structures
- Rearchitecting LLMsIn early access (MEAP)
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.
- arrayAn array is an ordered collection of elements organized in one or more dimensions and accessible by position or index.
- backpropagationBackpropagation is reverse-mode differentiation that propagates derivatives backward through a computational graph to compute gradients of an output or loss with respect to inputs and parameters.
- 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.
Related concepts
- rank-4 tensorproduces · A rank-4 tensor is a tensor with four axes, formed by stacking rank-3 tensors along an additional axis.
Questions about tensor
What is tensor?
A tensor is a multidimensional numerical array whose values are arranged along indexed dimensions and can be manipulated through mathematical computation.
Which Manning books explain tensor?
Deep Learning with R, Third Edition, Natural Language Processing in Action, Second Edition, Learn Generative AI with PyTorch, Build AI Drug Discovery Pipelines, Grokking AI Algorithms, Second Edition, Build a Text-to-Image Generator (from Scratch), GPU Programming with Triton, Deep Learning with Python, Third Edition and 2 more.
What should I know before learning tensor?
Manning books that teach tensor usually introduce language model, array, backpropagation and machine learning first.
What kinds of tensor are there?
Kinds of tensor include 4d tensor, 5D tensor, constant tensor and eager tensor.
What is tensor also called?
Tensor is also called multidimensional array.
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.









