Support Centre

Model Training & Maintenance

Guides on how to create, improve and maintain Models in Re:infer, using platform features such as Discover, Explore and Validation

Introduction to 'Refine'

 

The third phase, and the final step of the training process, is called ‘Refine’. The purpose of this stage is to understand how your model is performing and refine it until it performs as required. This involves improving specific labels that are not performing as expected, ensuring you have captured all of the relevant label concepts, and making sure your training data is a balanced representation of the dataset as a whole.  


Re:infer is designed to be completely transparent to users when it comes to model performance, and very flexible when it comes to improving performance in areas that require it. For any use case, you want to be confident that your model captures an accurate representation of what's in your dataset, and this phase of the training helps ensure that you can be.


This section of the Knowledge Base will cover in detail the steps outlined below, but will begin with detailed explanations of precision and recall in Re:infer, how Validation works, and how to understand the different aspects of model performance.


Key steps

 

Review Model Rating - this step is about checking your Model Rating in Validation and seeing where Re:infer thinks there may be performance issues with your model, as well as guidance on how to address them. This section includes detail about understanding and improving model performance.


Refine label performance - this step is about taking actions, recommended by Re:infer, to improve the performance of your labels. These include using the 'Check label' and 'Missed label' training modes, which help you address potential inconsistencies in your labelling, as well as 'Teach label' mode (covered in more detail in the Explore phase here)


Increase coverage - this step helps ensure that as much of your dataset as possible is covered by meaningful label predictions.


Improve balance - this step is about ensuring that your training data is a balanced representation of the dataset as a whole. Improving the balance in the dataset helps to reduce labelling bias and increase the reliability of predictions made by Re:infer.


Next: Precision and recall explained

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.

Sections

View all