Daniel Gissin
YOU?
Author Swipe
View article: The Implicit Bias of Depth: How Incremental Learning Drives Generalization
The Implicit Bias of Depth: How Incremental Learning Drives Generalization Open
A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We f…
View article: Discriminative Active Learning
Discriminative Active Learning Open
We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose e…