MACHINE_LEARNING

Machine learning section [Edit on GitHub]

Subsections

Keywords

Keyword descriptions

DESCRIPTOR: enum = POTENTIAL

Valid values:

  • POTENTIAL Eigenvalues of local potential matrix

  • OVERLAP Eigenvalues of local overlap matrix

  • R12 Distance between two atoms (just for testing)

References: Zhu2016

Descriptor used as input for machine learning. [Edit on GitHub]

GP_NOISE_VAR: real = 1.00000000E-001

Variance of noise used for Gaussian Process machine learning. [Edit on GitHub]

GP_SCALE: real = 5.00000000E-002

Mentions:PAO-ML

Length scale used for Gaussian Process machine learning. [Edit on GitHub]

METHOD: enum = GAUSSIAN_PROCESS

Valid values:

  • GAUSSIAN_PROCESS Gaussian Process

  • NEURAL_NETWORK Neural Network

  • LAZY Just rely on prior

Machine learning scheme used to predict PAO basis sets. [Edit on GitHub]

PRIOR: enum = ZERO

Valid values:

  • ZERO Simply use zero

  • MEAN Use average of training-set

Prior used for predictions. [Edit on GitHub]

TOLERANCE: real = 1.00000000E-002

Maximum variance tolerated when making predictions. [Edit on GitHub]