Index Ai Academy
Glossary · Phase 2 · Math for ML engineers

Cholesky factor

A triangular matrix L with L times its transpose equal to a covariance matrix. It turns standard noise into correlated noise.

Try it now

Learn it properly

Covariance matrices and the multivariate normal · Covariance and correlation, curves, outliers and common causes, rank correlation, skew and kurtosis. About 40 minutes.

Other terms from the same lesson

  • correlation: Covariance divided by both standard deviations: a number from -1 to 1 for how closely two variables follow a straight line.
  • kurtosis: How heavy a distribution's tails are: how often extreme values appear compared with a normal distribution.
  • positive semi-definite: A symmetric matrix that never gives a negative value for vᵀAv. Every covariance matrix is one.
  • Simpson's paradox: A relationship that points one way within every group and the other way when the groups are pooled.
  • skewness: How lopsided a distribution is. Right-skewed data has a long upper tail, which pulls the mean above the median.
  • Spearman correlation: Pearson's correlation computed on ranks: it measures whether two numbers always move the same way, and resists outliers.
  • whitening: Transforming data so its features are uncorrelated and each has variance 1.
Keep learning

More in plain English.

1286 terms in the glossary, each with the lesson that teaches it.

1286 terms

The glossary

Every word you'll meet in AI and machine learning, explained in everyday language.

Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write