Analysis

Intel DAAL analysis algorithms are intended to uncover the underlying structure of a data set and to characterize it by a set of quantitative measures, such as statistical moments, correlations coefficients, and so on. Some of the analysis algorithms also simplify the data: they transform, aggregate, or decompose that data in such a way that the transformed (aggregated or decomposed) data becomes easier to understand and characterize.

• Moments of Low Order
  
• Quantile
  
• Correlation and Variance-Covariance Matrices
  
• Cosine Distance Matrix
  
• Correlation Distance Matrix
  
• K-Means Clustering
  
• Principal Component Analysis
  
• Cholesky Decomposition
  
• Singular Value Decomposition
  
• Association Rules
  
• QR Decomposition
  
• Expectation-Maximization
  
• Multivariate Outlier Detection
  
• Univariate Outlier Detection
  
• Kernel Functions
  
• Quality Metrics
  
• Sorting