Intel® oneAPI Data Analytics Library
Learn from community members on how to build compute-intensive applications that run efficiently on Intel® architecture.
222 Discussions

Intel(R) DAAL 2019 Update 3 is now available


Intel(R) DAAL 2019 Update 3 is now available. Intel DAAL 2019 packages are now ready for download. Intel DAAL is available as part of the Intel(R) Parallel Studio XE and Intel(R) System Studio. Please visit the


What's New in Intel(R) DAAL 2019 Update 3:

  • Gradient Boosting training stage performance improvements for inexact split mode.
  • How to build reduced-size library on resource-constrained devices can be found here.
  • New parameter nTrials was introduced for K-means++ initialization. It allows to set number of trials to generate all clusters but the first initial cluster.
  • Improved performance for Cholesky algorithm
  • SAGA optimization solver is available to optimize non-smooth objective functions which are used for L1 regularized Logistic Regression, LASSO, ElasticNet algorithms.
  • Currently DAAL Logistic Regression with L1 penalty is supported by SAGA solver.
  • Intel offers several AI software tools and libraries on Amazon Web Services* Marketplace, including some of the most popular algorithmic optimizations from the Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) and from BigDL, a distributed deep learning library for Apache Spark*.
  • Deprecation Notice:With the introduction of daal4py, a package that supersedes PyDAAL, Intel is deprecating PyDAAL and will discontinue support starting with Intel DAAL 2021 and Intel Distribution for Python 2021.Until then Intel will continue to provide compatible pyDAAL pip and condapackages for newer releases of Intel DAAL and make it available in open source. However, Intel will not add the new features of Intel DAAL to pyDAAL. Intel recommends developers switch to and use daal4py.

Check Intel(R) DAAL 2019 release notes to learn more information

0 Kudos
0 Replies