khalib is a classifier calibration algorithm based on Khiops
Study and Implementation of various neural network pruning techniques. Extending the lottery ticket hypothesis to structured pruning for accelerated training while maintaining uncertainty and accuracy. The focus is on simplifying the model's complexity without sacrificing its overall performance or leading to overfitting.
Add a description, image, and links to the reliability-diagram topic page so that developers can more easily learn about it.
To associate your repository with the reliability-diagram topic, visit your repo's landing page and select "manage topics."