Browse Teach Curate

Nonnegative Matrix Factorization in Machine Learning

The decomposition of a nonnegative data matrix into a product of two lower-rank nonnegative factors, yielding parts-based, interpretable representations. It is formulated as a nonconvex optimization over the factor matrices and is widely used for feature extraction and dimensionality reduction.

Default Guide Video

Multiplicative Update Rules for Non-Negative Matrix Factorization

Non-negative matrix factorization (NMF) decomposes a non-negative matrix X (n×m) into two non-negative matrices W (n×k) and H (k×m) by minimizing the distance between X and WH subject to non-negativi…