Search Results for author:
Found 2 papers, 1 papers with code
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
Transfer learning and ensembling are two popular techniques for improving the performance and robustness of neural networks.
On the Memorization Properties of Contrastive Learning
Memorization studies of deep neural networks (DNNs) help to understand what patterns and how do DNNs learn, and motivate improvements to DNN training approaches.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
