PURF: Improving teacher representations by imposing smoothness constraints for knowledge distillation
- 9 April 2024
- journal article
- research article
- Published by Elsevier in Applied Soft Computing
- Vol. 159
Abstract
No abstract availableKeywords
Funding Information
- IITP
This publication has 72 references indexed in Scilit:
- Multi-view Teacher–Student NetworkNeural Networks, 2022
- Weak sub-network pruning for strong and efficient neural networksNeural Networks, 2021
- Uncertainty propagation for dropout-based Bayesian neural networksNeural Networks, 2021
- Diversity-driven knowledge distillation for financial trading using Deep Reinforcement LearningNeural Networks, 2021
- Asynchronous dissipative filtering for nonhomogeneous Markov switching neural networks with variable packet dropoutsNeural Networks, 2020
- Regularization of deep neural networks with spectral dropoutNeural Networks, 2019
- Adversarial Network Compression2019
- Learning Deep Representations with Probabilistic Knowledge Transfer2018
- Self-supervised Knowledge Distillation Using Singular Value Decomposition2018
- Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural networkNeural Networks, 2018