Tensor operation
A tensor operation is a mathematical or computational transformation applied to one or more tensors, producing tensor or scalar values.
Deep Learning with R, Third Edition
A tensor operation is a mathematical or computational transformation that takes one or more tensors as input and produces tensor values.
- How it is used
- Builds neural-network layers from operations on numeric tensors.
- How deep it goes
- Explains dense-layer operations and geometric interpretations through code and figures, without formal mathematical derivations.
- Examples
- Uses a dense-layer expression, PyTorch tensor functions, and 2D translation, rotation, and scaling figures.
- What you can do after
- Apply it via PyTorch to assemble a dense-layer function and compute gradients with backward().
Read how Deep Learning with R, Third Edition explains tensor operation →
Deep Learning with Python, Third Edition
An elementary array/tensor computation such as matrix multiplication, rectified linear activation, or normalization used as a building block in neural networks.
- How it is used
- Builds neural-network layers from numerical transformations applied to tensors.
- How deep it goes
- Explains dense-layer composition and practical TensorFlow operations, then connects differentiability to gradients without deriving their mathematics.
- Examples
- Demonstrates a dense function using matmul, bias addition, and ReLU, plus TensorFlow square, square-root, and concatenation calls.
- What you can do after
- Build it from scratch as a dense computation and retrieve gradients for differentiable tensor expressions with GradientTape.
Read how Deep Learning with Python, Third Edition explains tensor operation →
Deep Learning with PyTorch, Second Edition
An operation provided by PyTorch that acts on tensor data, either as a torch-module function or as a tensor method.
- How it is used
- Organizes PyTorch tensor manipulation for preparing data and working with tensors in deep-learning workflows.
- How deep it goes
- Defines operation families and demonstrates transpose and in-place behavior, but defers exhaustive API coverage to the documentation.
- Examples
- Demonstrates transpose through module and method calls, zeroing a tensor in place, and indexing and mutating a Python list.
- What you can do after
- Apply it via PyTorch by selecting tensor APIs, choosing functional or method syntax, and recognizing operations that mutate inputs.
Read how Deep Learning with PyTorch, Second Edition explains tensor operation →
Related concepts
- tensoruses · A tensor is a multidimensional, array-like structure of values indexed along zero or more dimensions and used for numerical computation.
- ReLUincludes · ReLU, or rectified linear unit, is an activation function that maps an input x to max(0, x).
- geometric transformationkind of · A geometric transformation is a mapping or operation that changes or expresses the position, orientation, scale, shape, or coordinate representation of geometric objects.
- translationimplements · A translation is a geometric transformation that moves every point by the same displacement without changing an object’s shape or orientation.
- language modelused 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.
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.