Released: November 15, 2017
- Graphical user interface supports a number of additional visualization types, an examples repository browser, and considerably improved interoperation with the Dakota command-line interface.
- Substantial improvements to multi-level and multi-fidelity methods, including greater flexibility in algorithm / model hierarchy combinations, separate base vs. multi-* methods with individualized specifications, multilevel data imports, option for recursive PCE emulation of discrepancies, and modular use of multi-* methods within Bayesian inference and nested contexts.
- Dakota now requires a C++11-compliant compiler, together with CMake 3.1 or newer (recommend 3.6 or greater). Dakota was updated to support a number of modern C++11-compliant compilers.
See complete list of Dakota 6.7 Release Notes.