3 papers
cs.CL2019
Self-Knowledge Distillation in Natural Language Processing
Sangchul Hahn, Heeyoul Choi
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in…
cs.LG2018
Disentangling Latent Factors of Variational Auto-Encoder with Whitening
Sangchul Hahn, Heeyoul Choi
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model…
cs.LG2018
Understanding Dropout as an Optimization Trick
Sangchul Hahn, Heeyoul Choi
As one of standard approaches to train deep neural networks, dropout has been applied to regularize large models to avoid overfitting, and the improvement in performance by dropout…