Using the Training app

Construct a feature matrix and define training and test datasets from data stored in Granta MI, then send the untrained model to the Intellegens Alchemite engine for training and testing.

Create a new model
Edit or retrain a model
Delete a model

Tip: In MI Machine Learning, the process for defining and training a model is as follows:

Create a new untrained model, or clone an existing trained or untrained model.
Choose a Granta MI database and primary table.
Define and populate the model Matrix. A Matrix contains attributes, links and records from Granta MI, and is converted into a feature matrix before being sent to the engine.
Send the model to the engine for training, and track progress with the Job Queue.

Once your model is trained, you can use the other MI Machine Learning apps to visualize the model, or apply a set of constraints (for example, optimizing an additive manufacturing process to produce materials with the desired properties).