Machine Learning CDT3D

From crtc.cs.odu.edu
Revision as of 07:55, 30 March 2018 by Ctsolakis (talk | contribs) (Early results using AutoMOMML with CDT3D)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

AutoMOMML

AutoMOMML: Automatic Multi-Objective Modeling with Machine Learning

AutoMOMML, an end-to-end, machine-learning-based framework to build predictive models for objectives such as performance, power, and energy. [1]

Machine learning classification.png

Early results using AutoMOMML with CDT3D

Output Parameters Correlation

Output Parameters Correlation

Variable importance classification

Variable importance classification for number of tetrahedra

Automomml varimp rf NIterations.png

Variable importance classification for number of iterations


Automomml modsel cv NTets.png

Model selection for number of tetrahedra


Model selection for number of iterations