layg.emulator.torch_emulator.TorchEmulator¶
-
class
layg.emulator.torch_emulator.
TorchEmulator
¶ Class that uses pytorch to do emulation
The Universal Approximation Theorem says that any Lebesgue integrable function can be approximated by a feed-forward network with sufficient layers of sufficient width. It doesn’t guarantee that we can train the network though.
Methods
add_data
(self, x_train, y_train)Add data to the training set on the fly set_emul_error_func
(self, x_cv, y_cv_err)Fit a quadratic to the residuals and mean distance to nearby points set_emul_func -
__init__
(self)¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__
(self)Initialize self. add_data
(self, x_train, y_train)Add data to the training set on the fly set_emul_error_func
(self, x_cv, y_cv_err)Fit a quadratic to the residuals and mean distance to nearby points set_emul_func
(self, x_train, y_train)-