Build NeurEco Discrete Dynamic model with GUI

• Fill in the Settings tab, the build parameters are explained in the table below:

  

  Settings to build a Discrete Dynamic model

• Press Build button

• Once the Build started, the Training, Evaluation, Metrics and Export panels become available. The moment the first model is saved to the checkpoint, these panels can be used as usual.

Build parameters

Minimum Settings to build a Discrete Dynamic model

Name	Description
Training Data	Required. Data used to train a model. Click on Add files and choose paths to the files prepared according to Data preparation for NeurEco Discrete Dynamic with GUI
Validation Data	Optional. Data used to validate a model. If not provided, the Validation Data are chosen automatically among the provided samples in Training Data
Testing Data	Optional. Data never used during the training process. If provided, allow to monitor the model performance on the test data during the Build.
Input normalization: Shift type	Default = mean. Possible values: none, mean. See Data normalization for Discrete Dynamic for more details.
Input normalization: Scale type	Default = l2. Possible values: none, l2. See Data normalization for Discrete Dynamic for more details.
Input normalization: normalize per feature	Default = True. If True, normalizes each input feature independently from others. See Data normalization for Discrete Dynamic for more details.
Output normalization: Shift type	Default = mean. Possible values: none, mean. See Data normalization for Discrete Dynamic for more details.
Output normalization: Scale type	Default = l2. Possible values: none, l2. See Data normalization for Discrete Dynamic for more details.
Output normalization: normalize per feature	Default = True. If True, normalizes each output feature independently from others. See Data normalization for Discrete Dynamic for more details.
Validation data percentage	Default = 30.0. Percentage of the data that NeurEco selects to use as Validation Data. Ignored when Validation Data are provided explicitly.

Advanced parameters

Advanced Settings to build a Discrete Dynamic model

Name	Description
steady input	forces the built model to be stable when fed with this input value
steady output	stable output value associated to input value of steady input
min hidden states	Default = 1, defines starting number of hidden states, it can accelerate the best topology identification process
max hidden states	Default = 0, defines the maximum number of hidden states, it can accelerate the best topology identification process. Is not taken into account when set to 0.

Data normalization for Discrete Dynamic

Set normalize per feature to True if trying to fit the features of different natures (temperature and pressure for example) and want to give them equivalent importance.

Set normalize per feature to False if trying to fit the features of the same nature (a set of temperatures for example) or a field.

If neither of provided normalization options suits the problem, normalize the data your own way prior to feeding them to NeurEco (and deactivate normalization by setting the scale and shift to none).

A normalization operation for NeurEco is a combination of a \(shift\) and a \(scale\), so that:

\[x_{normalized} = \frac{x-shift}{scale}\]

Allowed shift methods for NeurEco and their corresponding shifted values are listed in the table below:

NeurEco Discrete Dynamic shifting methods

Name	shift value
none	\[0\]
mean	\[mean(x)\]

Allowed scale methods for NeurEco Tabular and their corresponding scaled values are listed in the table below:

NeurEco Discrete Dynamic scaling methods

Name	scale value
none	\[1\]
l2	\[\frac{\left\Vert x\right\Vert }{\sqrt{size \_ of \_ x}}\]

Control the size of the NeurEco Discrete Dynamic model during Build

At any given moment of time the state of the system is represented by a vector, that stores the so-called hidden states of the system. In the state-space representation the hidden states are the state variables.

NeurEco Discrete Dynamic allows imposing the limits on the number of hidden states. When these limits rely on some additional knowledge about the system, it can facilitate the model training and reduce the time of Build.

Imposing the maximum number of hidden states, by setting the parameter max hidden states in Advanced settings, can decrease the size of the constructed model. That is what one is looking for when seeking a trade-off between accuracy and augmenting the embeddability of the model even more.

See Advanced build tutorial for an example of usage.