Home
Reference Guides
Reference guides are available for functions and commands supported by OML, Tcl, and Python.
romAI
Post-Processor Tab
The Post-Processor tab lets you visualize and evaluate the trained ROM.
Define Hyper Planes
Generate Scatter Plots of Predictions vs Target
These plots require data from a dataset file.

Welcome
What's New
Discover new features and enhancements.
Get Started
Discover Compose, including its language support and system requirements.
Tutorials
The Compose tutorials and associated example model files help introduce you to the basic functionality of the software.
User Guide
Learn about the features and functionality available in Compose.
Reference Guides
Reference guides are available for functions and commands supported by OML, Tcl, and Python.
- Scripting Guide for OpenMatrix Language
  OpenMatrix is a mathematical scripting language.
- Reference Guide for OpenMatrix Language Functions
  The Reference Guide contains documentation for all functions supported in the OpenMatrix language.
- Python in Compose Reference Guide
- romAI
  - Introduction
    romAI is an application that is comprised of libraries from the Altair Composeand Altair Twin Activate software products.
  - Design Fundamentals
    romAI serves two purposes.
  - Theoretical Framework
    Some system theory terminology must be understood.
  - ROM Framework
  - Workflow
    The typical workflow has four steps.
  - Installation
    The romAI tool is enabled through Extension Manager.
  - GUI
    The first steps of the workflow are accomplished through the GUI.
  - Pre-Processor Tab
    The Pre-Processor tab contains the optional pre-processing step.
  - Builder Tab
    The Builder tab facilitates the training step.
  - Post-Processor Tab
    The Post-Processor tab lets you visualize and evaluate the trained ROM.
    - Check Loss
      View the overall training, validation, and test loss.
    - Check Accuracy
      The R² Accuracy check is applicable only for static models.
    - Define Hyper Planes
      - Generate Hyper Planes
      - Generate Scatter Plots of Predictions vs Target
        These plots require data from a dataset file.
    - Time Simulation Tab
      If romAI is used to generate dynamic ROMs, it is important to have a tool that easily performs preliminary time simulations to assess the accuracy of the transient behavior after the romAI model has been trained.
    - Instance Evaluation Tab
      romAI can be used to generate static ROMs.
    - Report Generation
      The report generation tools can be accessed from Tools menu.
  - ROM Generation Tips
  - Batch Training
    The training procedure can be carried over without using the GUI.
  - Batch Execution
    The simulation and evaluation of a romAI model can be also done via batch in the Compose OML editor without the need to deploy the trained romAI model into a Twin Activate block, using the romAI_execute function.
  - Frequently Asked Questions
Appendix
Get help for the optional libraries that are available in the Extension Manager.
Frequently Asked Questions
You've got questions? We've got answers!

Generate Scatter Plots of Predictions vs Target

These plots require data from a dataset file.

To create Scatter Plots of Predictions vs Targets, select a test dataset file.

Note: The format and labels used in the file are the same as the ones used for training. Otherwise, an error dialog box shows up.
Select the Predict on Dataset check box.

Note: The edit boxes, menu, and slider on the Hyper Planes panel are invisible in case of the Predict on Dataset option.
Select the desired inputs and state variables from the Inputs/States box to create the x- and y-axes.
Select the Outputs that you want to evaluate and compare.
Enter the Downsample Ratio.
The downsample value determines the number of points in the dataset file that will be used for the evaluation/comparison. For example:
- A downsample ratio of 1 means that the comparison between the romAI output and the target (contained in the dataset) will be performed for all the points in the dataset file.
- A downsample factor of 0.1 means that the comparison between the romAI output and the target (contained in the dataset) will be performed for a tenth of the points in the dataset file.
- When a dataset file is very large, adjusting the downsample ratio can greatly improve the plot performance. By default a downsample ratio value less than 1 is used on initial plots when the dataset is large.
To resume plotting hyper planes, deselect the Predict on Dataset check box.