Buscar recursos académicos

In this work we show that global topological properties of co-occurrent word networks constructed from texts, seem to be the fingerprint of meaningful sentences. We observe that many statistical properties of these netwo...

Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains ...

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers...