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.
mnist-dataset
uncertainty-quantification
cifar10
accuracy-analysis
pruning-algorithms
monte-carlo-drop-out
reliability-diagram
expected-caliberation-error
make-moons
-
Updated
Feb 3, 2024 - Jupyter Notebook