Felipe del Río

RL1, Publisher:, Link>


Antonio Ossa-Guerra, Denis Parra, Felipe del Río, Manuel Cartagena, Patricio Cerda-Mardini


This tutorial serves as an introduction to deep learning approaches to build visual recommendation systems. Deep learning models can be used as feature extractors, and perform extremely well in visual recommender systems to create representations of visual items. This tutorial covers the foundations of convolutional neural networks and then how to use them to build state-of-the-art personalized recommendation systems. The tutorial is designed as a hands-on experience, focused on providing both theoretical knowledge as well as practical experience on the topics of the course.

32 visualizaciones Ir a la publicación

RL1, Publisher: arXiv, Link>


Álvaro Soto, Cristóbal Eyzaguirre, Felipe del Río, Vladimir Araujo


Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need to develop new or complementary strategies to increase the efficiency of these models. In this paper we propose DACT-BERT, a differentiable adaptive computation time strategy for BERT-like models. DACT-BERT adds an adaptive computational mechanism to BERT's regular processing pipeline, which controls the number of Transformer blocks that need to be executed at inference time. By doing this, the model learns to combine the most appropriate intermediate representations for the task at hand. Our experiments demonstrate that our approach, when compared to the baselines, excels on a reduced computational regime and is competitive in other less restrictive ones.

26 visualizaciones Ir a la publicación