User Guide
This user guide is here to help you get started with the software and understand what it can do. It explains the various features and functions in simple terms and provides straightforward code examples that you can use to create your own models.
The easiest way to understand the AIXD workflow is through the step-by-step example on the Getting started page, where these steps are demonstrated using a simple analytical use case.
Besides, this documentation contains additional information that will help you to understand the package and its features in more detail.
Summary of the Workflow
For utilizing the AIXD package for your project, follow these 4 steps:
Problem definition: Define your design parameters (\(X\)) and performance attributes (\(Y\)).
Dataset creation & analysis: Import your data or sample your design space. Use the available methods to analyse your data.
Model: Set-up, training & evaluation: Set up and train the model of your choice on the training dataset. Then evaluate the performance of your trained model on the test dataset quantitatively and visually.
Deployment: Deploy your finalized model to your design project - explore efficiently the space of designs.
Further information
Besides, we provide more detailed information on some of the modules of AIXD:
Plotter: Different tools to visualize your data, model performance and generation capabilities.
Sampler: Implementation details of the sampling methods available.
Sensitivity Analysis: A more detailed explanation of the sensitivity analysis methods implemented.