Build NeurEco Parametric Frequency Sweep model with the command line interface

To build a NeurEco Parametric Frequency Sweep model, run the following command in the terminal:

neurecoFNN build path/to/build/configuration/file/build.conf

The skeleton of a configuration file required to build NeurEco Parametric Frequency Sweep model, here build.conf, looks as follows. Its fields should be filled according to the problem at hand.

{
"neurecoFNN_build":
    {
                "AdvancedSettings": {
        },
        "checkpoint_address": "",
        "input_filenames": [],
        "output_filenames": [],
        "resume": false,
        "settings": {
            "compressed_space_size": 10,
            "enrichment_rate": 0.2,
            "max_number_of_enrichments": 200,
            "min_number_of_enrichments": 10,
            "unsuccessful_enrichments": 4,
            "validation_percentage": 30
        }
        "test_input_filenames": [],
        "test_output_filenames": [],
        "validation_input_filenames": [],
        "validation_output_filenames": [],
        "write_model_to": ""
    },
}

The available building parameters in the configuration file are described in the following table.

NeurEco Parametric Frequency Sweep building parameters in .conf

Name	type	description
checkpoint_address	string, default = “”	The path where the checkpoint model will be saved. The checkpoint model is used for resuming the build of a model, or for choosing an intermediate network with less topological optimization steps.
input_filenames	list of strings, default = []	training data: contains the input data in form of the paths of all the input data files (.conf). The format of the files can be csv, npy or mat (matlab files).
output_filenames	list of strings, default = []	training data: contains the target data in form of the paths of all the target data files. The format of the files can be csv, npy or mat (matlab files).
compressed_space_size	int	Default = \(5\), Dimension of reduced space of outputs to use to train the model.
enrichment_rate	Float in range \([0,1]\), default = \(0.2\)	Rate of enrichment. If is set to \(0\), the enrichment is conducted by one transformation at a time, il set to \(1\), all current possible transformations are performed together.
max_number_of_enrichments	int, default = \(200\)	Maximum number of enrichment steps to perform during the model construction.
min_number_of_enrichments	int, default = \(10\)	Minimum number of enrichment steps to perform during the model construction.
unsuccessful_enrichments	int, default = \(4\)	Stagnation criterium: tolerated number of subsequent enrichments without model improvement.
valid_percentage	float, min=1.0, max=50.0, default=30	Defines the percentage of the data that will be used as validation data. (NeurEco will automatically choose the best data for validation, to ensure that the created model will have the best fit on unseen data. The modification of this parameter can be of interest when the data set is small and we have to find a good tradeoff between the learning and the validation sets.). This parameter is ignored if validation_exc_filenames and validation_output_filenames are passed.
test_input_filenames	list of strings, default = []	Contains the paths of all the testing input data files. The format of the files can be csv or npy.
test_output_filenames	list of strings, default = []	training data: contains the target data in form of the paths of all the target data files. The format of the files can be csv, npy or mat (matlab files).
validation_input_filenames	list of strings, default = [] (GUI, .conf)	validation data: contains the validation input data table in form of the paths of all the validation input data files. The format of the files can be csv or npy.
validation_output_filenames	list of strings, default = [] (GUI, .conf)	validation data: contains the paths of all the validation target data files. The format of the files can be csv or npy.
write_model_to	string, default = “”	the path where the model will be saved.