What is Under the Hood
gpCAM is an advanced Gaussian process tool, combined with HPC mathematical optimization.
Its power comes from the fact that most parts of the Gaussian process and the steering can be defined by the user as they become more familiar with the underlying mathematics. One could imagine a car engine; the motor block is the core code of gpCAM, all other parts that make a well-working car engine are supplied, but they can be exchanged to create the perfect engine for a particular purpose. Some of the building blocks that can be defined by the user and imported into gpCAM are
A data acquisition function that tells gpCAM where data is sent to and received from
A plotting function for visualization
A kernel function to constrain the set of model functions
A parametric mean function to encapsulate a physics-based model
An optimizer that replaces the standard optimizers, for instance, for constrained training
An objective function (or acquisition function) to ingest what patterns the practitioner is looking for
A cost function to make sure measured points will minimize a cost while maximizing knowledge gain
All this flexibility means that gpCAM naturally includes the ability for physics awareness and also multi-task learning.
Torch and DASK based high-performance computing means that gpCAM can take full advantage of supercomputers.
Read More Here:
Many of the recent features are not published yet. The papers will be linked here soon.