Synthesis Modeling: The Intersection of HPC and Machine Learning
Solving previously intractable problems and reduce costs
Get an Alertwhen The Register has something new about ...
Check the boxes & select Email or Atom/RSS Feed.
Historically, numerical analysis has formed the backbone of supercomputing for decades by applying mathematical models of first-principle physics to simulate the behavior of systems from subatomic to galactic scale. Recently, scientists have begun experimenting with a relatively new approach to understand complex systems using machine learning (ML) predictive models, primarily Deep Neural Networks (DNN), trained by the virtually unlimited data sets produced from traditional analysis and direct observation. Early results indicate that these “synthesis models,” combining ML and traditional simulation, can improve accuracy, accelerate time to solution and significantly reduce costs.
This paper examines how machine learning is being used as a new tool for scientific discovery, augmenting traditional techniques to improve our understanding of the universe. As scientists become more comfortable with this new approach, and as the methodologies become more robust, we believe that machine learning has the potential to emerge as a mainstream tool for many areas of scientific computing.