Foundations

SVD (Singular Value Decomposition)

Factorisation A = UΣVᵀ that exists for any matrix: a rotation, an axis-aligned scaling, then another rotation.

Why interviewers ask about it

PCA is the SVD of the mean-centred data matrix. Never form the covariance matrix explicitly - it squares the condition number.

Freezing pretrained W and learning ΔW = (α/r)·BA with B initialised to zero, training ~0.1–2% of parameters.

This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.