|
|
|
|
|
|
 |
|
|
machine learning framework 1.5 for Mathematica: The Multi-Platform Tool for Creating Interpretable, Computational Models from Data
|
|
|
|
|
|
|
|
|
|
|
|
2006 Wolfram Technology Conference
|
|
|
|
|
|
Champaign IL
|
|
|
|
|
|
machine learning framework (mlf) for Mathematica is a collection of powerful machine learning algorithms integrated into a framework for the purpose of data analysis. The framework allows for combining different machine learning algorithms to solve one single problem. The algorithms are highly parameterizable and implemented in an efficient core engine—realized in C++. mlf for Mathematica combines a large variety of distinct algorithms in an optimized computational kernel and the manipulation, descriptive programming, and graphical capabilities of Mathematica to give users unforeseen insights into their data. Driven by the needs of our industrial partners mlf is continuously developed to be able to create models from data that generate new knowledge. To make the mlf more accessible to our customers, mlf is now available on all three major operating systems: Windows, Mac OS, and Linux. To ensure the high quality of mlf, we developed a mulitplatform build and test environment that allows for continous integration. That is to automatically run builds and test suites whenever a new piece of code is added to mlf. Also the availability of the new Wolfram Workbench greatly contributes to the efficient development of mlf with its powerful editing, searching, and debugging features. In this presentation we will describe new features of the latest release of mlf (Version 1.5) as well as our approaches to multiplatform development and quality assurance.
|
|
|
|
|
|
|
|
|
|
|
|
|
| | | | | |
|
For the newest resources, visit Wolfram Repositories and Archives »
