Inheritance diagram for PND:

Public Member Functions
	PND ()

void	defineParams (int numberOfAtoms)

std::pair< torch::Tensor, torch::Tensor >	LossPreTrain (torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, int n, int Np, int d)

virtual std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	Loss (torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, torch::Tensor totalEnergy, torch::Tensor kineticEnergy, torch::Tensor potentialEnergy, int n, int Np, int d)

virtual std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	UpdateParamsNADAM (torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, torch::Tensor velocities, torch::Tensor S, torch::Tensor totalEnergy, torch::Tensor kineticEnergy, torch::Tensor potentialEnergy, int epoch, int n, int Np, int d, double alpha, double epsilon, torch::Tensor beta)

virtual std::pair< torch::Tensor, torch::Tensor >	mainTrain (torch::Tensor params, torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, int num_epochs, torch::Tensor totalEnergy, torch::Tensor kineticEnergy, torch::Tensor potentialEnergy, int n, int Np, int d, double learn_rate=0.0001, double momentum=0.99)

std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	UpdatePreParamsNADAM (torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, torch::Tensor velocities, torch::Tensor S, int epoch, int n, int Np, int d, double alpha=0.001, double epsilon=pow(10, -7), torch::Tensor beta=torch::tensor({0.999, 0.999}))

std::pair< torch::Tensor, torch::Tensor >	PreTrain (torch::Tensor t_seq, std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > icfs, int num_epochs, int n, int Np, int d, double learn_rate=0.001, double momentum=0.99)

Public Attributes
int	PreTrainEpochs

int	MainTrainEpochs

int	StepTrain

int	nodes

torch::Tensor	params

Constructor & Destructor Documentation

◆ PND()

PND::PND ( )

Constructor definition - prompts objects to read input file which specifies the number of time grids to predict, epochs for training and other network properties such as number of nodes.

Default input file /Source/pnd.in

Member Function Documentation

◆ defineParams()

void PND::defineParams ( int numberOfAtoms )

Method to define the number of atoms that the system comprises of. Used while reading the atom trajectories from the simulation data

Parameters

numberOfAtoms This is the number of atoms in the molecular dynamics simulation

◆ Loss()

std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > PND::Loss	(	torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		torch::Tensor	totalEnergy,
		torch::Tensor	kineticEnergy,
		torch::Tensor	potentialEnergy,
		int	n,
		int	Np,
		int	d
	)

virtual

Define a Loss function for the network which is a set of DEs governing the evolution of the system. Only method declaration provided, method must be defined when user's working class inherits from PND

Parameters

t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
totalEnergy	system total energy across time steps
kineticEnergy	system kinetic energy across time steps
potentialEnergy	system potential energy across time steps
n	Number of neurons in the NN
Np	Number of atoms in the MD system
d	dimensionality of the space (d = 3 when data in x,y,z co-ordinates is available)

Returns: returns a tuple of sum of gradients, mean squared error(MSE) loss, boundary loss, Least Action Loss, Hamiltonian Loss, momentum Loss

Reimplemented in ScratchPad.

◆ LossPreTrain()

std::pair< torch::Tensor, torch::Tensor > PND::LossPreTrain	(	torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		int	n,
		int	Np,
		int	d
	)

Define a Loss function for the network and before starting the main training task. Method can be overridden when class inherits from PND

Parameters

t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
n	number of neurons in the NN
Np	number of atoms in the MD system
d	dimensionality of the space (d = 3 when data in x,y,z co-ordinates is available)

Returns: returns the the tuple containing sum of gradients of outputs with respect to the input as specified in the DE as well and the root mean square(RMS) loss value

◆ mainTrain()

std::pair< torch::Tensor, torch::Tensor > PND::mainTrain	(	torch::Tensor	params,
		torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		int	num_epochs,
		torch::Tensor	totalEnergy,
		torch::Tensor	kineticEnergy,
		torch::Tensor	potentialEnergy,
		int	n,
		int	Np,
		int	d,
		double	learn_rate = `0.0001`,
		double	momentum = `0.99`
	)

virtual

Routine to follow for main-training the NN, i.e., training for the target data. Users may decide to call their parameter updating algorithm implementation in each training iteration.

Parameters

params	inital parameters of the NN which will be trained
t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
num_epochs	number of epochs for which training is to be carried out
totalEnergy	system total energy across time steps
kineticEnergy	system kinetic energy across time steps
potentialEnergy	system potential energy across time steps
n	number of neurons in the NN
Np	number of atoms in the MD system
d	number of atoms in the MD system
learn_rate	learning rate for optimizer
momentum	parameter to pass to the optimizer that uses momentum

Returns: the tuple of trained weights and mean loss value at the end of training

Reimplemented in ScratchPad.

◆ PreTrain()

std::pair< torch::Tensor, torch::Tensor > PND::PreTrain	(	torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		int	num_epochs,
		int	n,
		int	Np,
		int	d,
		double	learn_rate = `0.001`,
		double	momentum = `0.99`
	)

Routine to follow for pre-training the NN, i.e., training with a data set. Method definition trains the NN over a number of epochs with the UpdatePreParams(...) optimizer

Parameters

t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
num_epochs	number of epochs for which pre-trainig is to be carried out
n	number of neurons in the NN
Np	number of atoms in the MD system
d	dimensionality of the space (d = 3 when data in x,y,z co-ordinates is available)
learn_rate	parameter to pass to the optimizer
momentum	parameter to pass to the optimizer that uses momentum

Returns: the tuple of trained weights and mean loss value at the end of training

◆ UpdateParamsNADAM()

std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > PND::UpdateParamsNADAM	(	torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		torch::Tensor	velocities,
		torch::Tensor	S,
		torch::Tensor	totalEnergy,
		torch::Tensor	kineticEnergy,
		torch::Tensor	potentialEnergy,
		int	epoch,
		int	n,
		int	Np,
		int	d,
		double	alpha,
		double	epsilon,
		torch::Tensor	beta
	)

virtual

Defines an optimizer for adjusting the parameters in each main training iteration. We provide the declaration and method must be defined when user's working class inherits from PND

Parameters

t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
velocities
S
totalEnergy	system total energy across time steps
kineticEnergy	system kinetic energy across time steps
potentialEnergy	system potential energy across time steps
epoch	defines the number of steps
n	number of neurons in the NN
Np	number of atoms in the MD system
d	dimensionality of the space (d = 3 when data in x,y,z co-ordinates is available)
alpha	parameters for optimizers
epsilon	constant for stability
beta	parameters for optimizers

Returns: the tuple of trained weights and mean loss value at the end of training

Reimplemented in ScratchPad.

◆ UpdatePreParamsNADAM()

std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor > PND::UpdatePreParamsNADAM	(	torch::Tensor	t_seq,
		std::tuple< torch::Tensor, torch::Tensor, torch::Tensor, torch::Tensor >	icfs,
		torch::Tensor	velocities,
		torch::Tensor	S,
		int	epoch,
		int	n,
		int	Np,
		int	d,
		double	alpha = `0.001`,
		double	epsilon = `pow(10, -7)`,
		torch::Tensor	beta = `torch::tensor( {0.999, 0.999})`
	)

Defines an optimizer for adjusting the parameters in each pre-training iteration

Parameters

t_seq	time sequences for which the pre-training is carried out
icfs	initial and final positions and velocites that are to be used for the pre-training task
velocities
S
epoch	defines the number of steps
n	number of neurons in the NN
Np	number of atoms in the MD system
d	dimensionality of the space (d = 3 when data in x,y,z co-ordinates is available)
alpha	a parameter for optimizer
epsilon	constant for stability
beta	tuple with values for the exponential decay rate for the 1st moment estimates and exponential decay rate for the exponentially weighted infinity norm

Returns: tuple of optimized parameters, optimizer values and RMS loss value

The documentation for this class was generated from the following files:

Source/pnd.hpp
Source/pnd.cpp

Public Member Functions

Public Attributes

Constructor & Destructor Documentation

◆ PND()

Member Function Documentation

◆ defineParams()

◆ Loss()

◆ LossPreTrain()

◆ mainTrain()

◆ PreTrain()

◆ UpdateParamsNADAM()

◆ UpdatePreParamsNADAM()