2 papers
cs.CL2021
Regularizing Transformers With Deep Probabilistic Layers
Aurora Cobo Aguilera, Pablo Martínez Olmos, Antonio Artés-Rodríguez +1
Language models (LM) have grown with non-stop in the last decade, from sequence-to-sequence architectures to the state-of-the-art and utter attention-based Transformers. In this wo…
cs.LG2020
Robust Sampling in Deep Learning
Aurora Cobo Aguilera, Antonio Artés-Rodríguez, Fernando Pérez-Cruz +1
Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional ro…