ADMB-11.4
Released May 29, 2015
The ADMB (Automatic Differentiation Model Builder) software suite is an environment for nonlinear statistical modeling enabling rapid model development, numerical stability, fast and efficient computation, and high accuracy parameter estimates. AD Model Builder is a high level language built around the AUTODIF Library, a C++ language extension which transparently implements reverse mode automatic differentiation. A closely related software package, ADMB-RE, implements random effects in nonlinear models.
ADMB is an open source project. Read the AD Model Builder LICENSE.
ADMB is freely available for download. If you would like to contribute or donate funds, please contact users@admb-project.org.
Cool ADMB T-shirts are also available for purchase.
Fournier, D.A., H.J. Skaug, J. Ancheta, J. Ianelli, A. Magnusson, M.N. Maunder,
A. Nielsen, and J. Sibert. 2012. AD Model Builder: using automatic
differentiation for statistical inference of highly parameterized complex
nonlinear models. Optim. Methods Softw. 27:233-249.
The abstract and publication can be freely downloaded from the publisher.
Read release notes for changes and features in CHANGES.
Read the installation procedures in INSTALL for Unix and Windows computers.
User manuals for AD Model Builder, the AUTODIF library and the ADMB-RE nonlinear random effects module are in the ADMB downloads.
Additional documentation is also available on the ADMB website.
For help and support, email users@admb-project.org.
Mailing list archives
The ADMB software was originally developed by David Fournier of Otter Research Ltd.
Thanks to the following who have contributed to the ADMB Project by providing fixes and/or suggestions:
For help and support, email users@admb-project.org.