A machine learning model is essentially a mathematical representation of a real-world process. To create machine learning models, you need to provide machine learning algorithms with training data from which they can learn.
The Re:infer platform uses a number of machine learning models (both supervised and unsupervised) in order to interpret, understand and apply labels to your data. We often use the term 'model' in our platform and our documentation to refer collectively to these models working behind the scenes.
Every dataset has a 'model' associated with it, that is trained as users review verbatims within the platform. As the model trains, it learns and improves, enabling it to make better predictions for labels and entities.
Models can be saved and versioned. This means that when users set up an automation trigger, they can select a specific version of the model and can be confident in the performance of that version for the label in question. This gives users determinism when it comes to creating automations or using the data for analytics in downstream applications. For more information, see the models section.
Previous: Labels (predictions, confidence levels, hierarchy, etc.) | Next: Model Rating