liveBook · Manning

Linear transformation

A linear transformation is a mapping between vector spaces that preserves vector addition and scalar multiplication.

How 3 Manning books explain it

Grokking Bayes

A linear transformation is a mapping whose output is a linear combination of its inputs, possibly including an additive bias in an affine implementation.

How it is used
Explains how neural-network layers map data between nodes before nonlinear activation.
How deep it goes
Defines weights, biases, and layer connections but stops short of deriving the transformation or implementing it in code.
Examples
Uses a y = mx + b transformation and a multilayer architecture with hidden layers of sizes six and four.
What you can do after
Understand how weights and biases parameterize layer-to-layer mappings in a neural network.

Read how Grokking Bayes explains linear transformation →

Applied Reinforcement Learning

A linear transformation maps inputs to weighted combinations of those inputs, possibly with an added bias.

How it is used
Transforms each layer’s inputs before an activation in a deep network used to represent high-dimensional states.
How deep it goes
Defines the operation as weighted summation plus bias and explains why nonlinear activations are needed between layers.
Examples
Illustrates the operation through a neuron receiving inputs and computing a weighted sum plus bias.
What you can do after
Understand why neural network layers combine weighted inputs and why nonlinear activations add expressive power.

Read how Applied Reinforcement Learning explains linear transformation →

Geometry for Programmers

A linear transformation is a mapping in which each output coordinate is a linear combination of the input coordinates and the origin maps to the origin.

How it is used
Uses square-matrix multiplication to model rotation, scaling, and other origin-preserving geometric transformations.
How deep it goes
Explains coordinate formulas, matrix algebra, composition, inversion, and symbolic recovery, but stops short of formal proof.
Examples
Uses rotation and scaling formulas, Euclidean shape figures, and a SymPy system that recovers a matrix from two point mappings.
What you can do after
Build it from scratch by expressing coordinate mappings as matrices, composing them, inverting them, or solving for unknown entries.

Read how Geometry for Programmers explains linear transformation →

Related concepts

Questions about linear transformation

What is linear transformation?

A linear transformation is a mapping between vector spaces that preserves vector addition and scalar multiplication.

Which Manning books explain linear transformation?

Grokking Bayes, Applied Reinforcement Learning and Geometry for Programmers.

What is the difference between linear transformation and translation?

A linear transformation is a mapping between vector spaces that preserves vector addition and scalar multiplication. A translation is a geometric transformation that moves every point by the same displacement without changing an object’s shape or orientation.

What is linear transformation a kind of?

Linear transformation is a kind of geometric transformation. A geometric transformation is a mapping or operation that changes or expresses the position, orientation, scale, shape, or coordinate representation of geometric objects.

What are the parts of linear transformation?

Linear transformation includes edge.

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.