Hyperplane
A hyperplane is a flat affine subspace with dimension one less than its ambient space, capable of dividing that space into regions.
Geometry for Programmers
A hyperplane is a flat affine subspace of one dimension less than its surrounding space, such as a line in two dimensions or a plane in three dimensions.
- How it is used
- Interprets linear equations and systems as geometric intersections for reasoning about solutions.
- How deep it goes
- Defines hyperplane equations, classifies intersections, and relates them to solver behavior without deriving general algorithms.
- Examples
- Uses intersecting train routes, parallel and coincident lines, room planes, computed tomography, and intersecting 3D planes.
- What you can do after
- Evaluate/understand whether a linear system has a point, continuum, or no geometric intersection.
Math and Architectures of Deep Learning
A flat boundary of one dimension less than the ambient space.
- How it is used
- Uses hyperplanes as linear decision boundaries for separating classes in machine-learning feature spaces.
- How deep it goes
- Defines the equation, normal vector, orthogonality, and sign-based regions, but defers training details.
- Examples
- Uses stock decisions in three dimensions, planar classifier diagrams, and perceptron-based class separation.
- What you can do after
- Evaluate a linear classifier by interpreting its weights, bias, normal direction, and signed distance side.
Read how Math and Architectures of Deep Learning explains hyperplane →
Grokking Machine Learning
A flat geometric subspace of one dimension less than its surrounding space that can separate points in higher-dimensional space.
- How it is used
- Represents a higher-dimensional perceptron classifier boundary that divides feature space into two prediction regions.
- How deep it goes
- Explains the dimensional analogy and classification boundary through weighted features, without a formal geometric derivation.
- Examples
- Uses alien sentences represented by word counts, including a three-feature point and a separating plane.
- What you can do after
- Understand how a perceptron uses a boundary to divide higher-dimensional feature vectors into two classes.
Machine Learning Algorithms in Depth
A hyperplane is a flat affine subspace whose dimension is one less than that of its ambient space.
- How it is used
- Uses hyperplanes as decision boundaries for binary linear classification.
- How deep it goes
- Defines the geometric role and classification rule, then stops short of deriving the point-to-hyperplane distance.
- Examples
- Illustrates a two-dimensional boundary and applies perceptron classification to the iris dataset.
- What you can do after
- Evaluate linear-classifier geometry by identifying class sides and computing point-to-hyperplane Euclidean distances.
Read how Machine Learning Algorithms in Depth explains hyperplane →
Advanced Algorithms and Data Structures
A hyperplane is a flat affine subspace of one dimension less than its surrounding space that divides the space into two half-spaces.
- How it is used
- Supports geometric partitioning in nearest-neighbor structures and reasoning about linear separability in clustering.
- How deep it goes
- Defines dimensionality and half-space division, then applies the idea to k-d trees and clustering without developing formal geometry.
- Examples
- Uses k-d tree partitions, linearly separated sets, and linear clusters contrasted with rings and spirals.
- What you can do after
- Evaluate whether geometric data partitions or clusters can be separated by a flat boundary.
Read how Advanced Algorithms and Data Structures explains hyperplane →
AI-Powered Search
A separating hyperplane is a flat boundary in a feature space that divides examples into regions associated with different classes or ranking outcomes.
- How it is used
- Separates relevant from irrelevant search examples and supplies feature weights for ranking.
- How deep it goes
- Defines geometric separation and connects it to ranking weights, while stopping short of an in-depth SVM treatment.
- Examples
- Uses dog-cat classification, height and weight, search-result features, feature deltas, and a LinearSVC implementation.
- What you can do after
- Evaluate how a learned boundary separates classes and interpret its orthogonal vector as ranking feature weights.
Related concepts
- decision boundarykind of · A decision boundary is the locus in input or feature space that separates regions assigned different classes or decision outcomes by a predictive model.
- linekind of · A line is a contiguous sequence of text characters ending at a line boundary or the end of a text stream.
- planekind of · A plane is a flat two-dimensional geometric surface extending indefinitely in two independent directions.
- dimensionkind of · A dimension is an independent coordinate, measurable axis, or descriptive attribute used to represent, locate, or analyze something.
- linear systemequivalent to · A linear system is a set of linear relationships among variables, commonly expressed as simultaneous equations or a linear transformation, for which superposition applies.
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.