Search Results for author:
Found 4 papers, 0 papers with code
Label-efficient audio classification through multitask learning and self-supervision
We demonstrate that, in scenarios with limited labeled training data, one can significantly improve the performance of three different supervised classification tasks individually by up to 6% through simultaneous training with these additional self-supervised tasks.
Generalization in multitask deep neural classifiers: a statistical physics approach
There has also been a recent interest in extending these analyses to understanding how multitask learning can further improve the generalization capacity of deep neural nets.
Illuminating Dark Knowledge via Random Matrix Ensembles
It is all but certain that machine learning models based on deep neural networks will soon feature ubiquitously in a wide variety of critical products and services that people rely on.
Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks
Motivated by a recent study on learning robustness without input perturbations by distilling an AT model, we explore what is learned during adversarial training by analyzing the distribution of logits in AT models.
