Uploaded image for project: 'Machine Learning Library'
  1. Machine Learning Library
  2. ML-205

ML Cluster Implementations using PB-BLAS

    XMLWordPrintable

    Details

    • Type: Improvement
    • Status: Open
    • Priority: Not specified
    • Resolution: Unresolved
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: None
    • Labels:

      Description

      A new version of Cluster for dense matrices is available that uses the BLAS libraries for the matrix calculations. This implementation provides significant speed up for cases where the values are dense, and the Euclidean distance measure is appropriate. Later improvements will include user supplied kernel functions for the distance measure to provide an effective clustering when the Euclidian distance metric is inappropriate. The implementation uses distributed partition matrices to achieve scale beyond the scale provided by a single system.

        Attachments

          Activity

            People

            • Assignee:
              johnholt John Holt
              Reporter:
              lorraineachapman Lorraine Chapman
            • Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

              Dates

              • Created:
                Updated: