Quantum kernels & learning theory
Four detailed lessons, mathematical definitions, worked examples and limitations.
Explore the lessons
Concept 17Fidelity quantum kernelsEncode data as states and measure state overlap to construct a positive semidefinite kernel in ideal conditions.Concept 18Quantum support vector machinesUse quantum-derived Gram matrices in classical margin-based SVM optimization.Concept 19Kernel concentrationIn high-dimensional Hilbert spaces, many generic state overlaps concentrate and lose discriminative power.Concept 20Generalization and inductive biasQuantum learning depends on task-aligned structure, effective dimension and the geometry induced by the feature map.