Search Results for author:
Found 2 papers, 2 papers with code
On Mixup Regularization
We show that Mixup can be interpreted as standard empirical risk minimization estimator subject to a combination of data transformation and random perturbation of the transformed data.
Ranked #75 on
Image Classification
on ObjectNet
(using extra training data)
Efficient softmax approximation for GPUs
We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
