Search Results for author:
Found 2 papers, 0 papers with code
SKDBERT: Compressing BERT via Stochastic Knowledge Distillation
In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT.
Understanding Why Neural Networks Generalize Well Through GSNR of Parameters
As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
