Goto

Collaborating Authors

 Country




Learning Conditional Deformable Templates with Convolutional Networks

Neural Information Processing Systems

In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute asingle template for the entire population of images, or a few templates for specific sub-groups of the data.



Alpine glacier holds history dating back to the Romans. And it's melting--fast.

Popular Science

Alpine glacier holds history dating back to the Romans. Scientists are racing to document 6,000 years of history stored inside the WeiรŸseespitze ice cap. The dark surface shows significant melting. Breakthroughs, discoveries, and DIY tips sent six days a week. Deep inside the frozen Eastern Alps, the WeiรŸseespitze ice cap (pronounced VICE-zay-shpitt-suh) sits at almost 11,482 feet (3,500 meters) above sea level.



MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models

Neural Information Processing Systems

Machine comprehension (MC) has gained significant popularity over the past few years and it is a coveted goal in the field of natural language understanding. Its task is to teach the machine to understand thecontent ofagivenpassage andthenanswer arelated question, which requires deep comprehension and accurate information extraction towards the text.