nnp_model Module Reference

Methods dealing with core routines for artificial neural networks. More...

Functions/Subroutines
subroutine, public	nnp_write_arc (nnp, para_env, printtag)
	Write neural network architecture information.
subroutine, public	nnp_predict (arc, nnp, i_com)
	Predict energy by evaluating neural network.
subroutine, public	nnp_gradients (arc, nnp, i_com, denergydsym)
	Calculate gradients of neural network.

Detailed Description

Methods dealing with core routines for artificial neural networks.

Author

Christoph Schran (chris.nosp@m.toph.nosp@m..schr.nosp@m.an@r.nosp@m.ub.de)

Date

2020-10-10

Function/Subroutine Documentation

nnp_write_arc()

subroutine, public nnp_model::nnp_write_arc	(	type(nnp_type), intent(in)	nnp,
		type(mp_para_env_type), intent(in)	para_env,
		character(len=*), intent(in)	printtag
	)

Write neural network architecture information.

Parameters

nnp	...
para_env	...
printtag	...

Definition at line 46 of file nnp_model.F.

Here is the call graph for this function:

Here is the caller graph for this function:

nnp_predict()

subroutine, public nnp_model::nnp_predict	(	type(nnp_arc_type), intent(inout)	arc,
		type(nnp_type), intent(inout)	nnp,
		integer, intent(in)	i_com
	)

Predict energy by evaluating neural network.

Parameters

arc	...
nnp	...
i_com	...

Definition at line 81 of file nnp_model.F.

Here is the caller graph for this function:

nnp_gradients()

subroutine, public nnp_model::nnp_gradients	(	type(nnp_arc_type), intent(inout)	arc,
		type(nnp_type), intent(inout)	nnp,
		integer, intent(in)	i_com,
		real(kind=dp), dimension(:), allocatable	denergydsym
	)

Calculate gradients of neural network.

Parameters

arc	...
nnp	...
i_com	...
denergydsym	...

Definition at line 168 of file nnp_model.F.

Here is the call graph for this function:

Here is the caller graph for this function: