AI engineering glossary · Classical ML algorithms
What is LSA (Truncated SVD)?
Truncated SVD (also called LSA): A dimensionality reduction method that keeps only the largest singular values of the data matrix. Unlike principal component analysis it does not centre the data first, so it works directly on sparse matrices such as word counts.
Truncated SVD: an example
Compressing a 100,000 by 50,000 sparse TF-IDF matrix to 200 columns.
Related terms
More Classical ML algorithms terms
- UMAP
- Variance inflation factor
- Voting classifier
- Weak learner
- XGBoost
- AdaBoost
- Agglomerative clustering
- Anomaly detection
Where you learn it
Truncated SVD is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.