August 21, 2015

MACROS 6.1 Release

DATADVANCE development team is pleased to announce the release of MACROS 6.1, a new stable version of the MACROS library and featured plug-ins.

Since this release, MACROS provides a Java interface to evaluate approximation models similar to the simple C interface added in MACROS 3.4. Required libraries are included into package, and the MACROS User Manual provides API documentation and usage example.

Other notable updates in MACROS 6.1:

  • Solving mixed-integer problems with GTOpt no longer requires using the surrogate based optimization (SBO) method, simplifying configuration of such problems.
  • Further improvement in dealing with cusp-like singularities in GTOpt, following the update of gradient-based optimization methods in MACROS 6.0.
  • New sparse linear regression technique added to GTApprox. This approximation method is based on elastic net regularization and is available as an option when using the RSM technique.
  • The Gradient Based Regression Trees (GBRT) technique was updated to improve quality of incremental model training.
  • Taguchi sensitivity analysis technique added to GTSDA. This method was developed to work with noisy output data and small samples, and shows best results when the sample is generated using the mixed orthogonal array technique added to GTDoE in MACROS 6.0.

MACROS 6.1 also fixes few minor bugs discovered since the MACROS 6.0 release. For full details on recent updates and bugfixes you can refer to the latest changelog, or contact us to receive more information and MACROS updates!

LinkedIn
VK

Interested in the solution?

Click to request a free 30-day demo.

Request demo