Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

Fast demographic traits promote high diversification rates of Amazonian trees

Abstract: The Amazon rain forest sustains the world's highest tree diversity, but it remains unclear why some clades of trees are hyperdiverse, whereas others are not. Using dated phylogenies, estimates of current species richness and trait and demographic data from a large network of forest plots, we show that fast demographic traits – short turnover times – are associated with high diversification rates across 51 clades of canopy trees. This relationship is robust to assuming that diversification rates are either constant or decline over time, and occurs in a wide range of Neotropical tree lineages. This finding reveals the crucial role of intrinsic, ecological variation among clades for understanding the origin of the remarkable diversity of Amazonian trees and forests.

Point Cloud GAN

Abstract: Generative Adversarial Networks (GAN) can achieve promising performance on learning complex data distributions on different types of data. In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable to point clouds, because the constraint required for discriminators is undefined for set data. We propose a two fold modification to GAN algorithm for learning to generate point clouds (PC-GAN). First, we combine ideas from hierarchical Bayesian modeling and implicit generative models by learning a hierarchical and interpretable sampling process. A key component of our method is that we train a posterior inference network for the hidden variables. Second, instead of using only state-of-the-art Wasserstein GAN objective, we propose a sandwiching objective, which results in a tighter Wasserstein distance estimate than the commonly used dual form. Thereby, PC-GAN defines a generic framework that can incorporate many existing GAN algorithms. We validate our claims on ModelNet40 benchmark dataset. Using the distance between generated point clouds and true meshes as metric, we find that PC-GAN trained by the sandwiching objective achieves better results on test data than the existing methods. Moreover, as a byproduct, PC- GAN learns versatile latent representations of point clouds, which can achieve competitive performance with other unsupervised learning algorithms on object recognition task. Lastly, we also provide studies on generating unseen classes of objects and transforming image to point cloud, which demonstrates the compelling generalization capability and potentials of PC-GAN.

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

Abstract: Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate contradiction. As exposed by several recent challenge datasets, these models perform poorly when such association is absent, e.g., predicting that "I love dogs" contradicts "I don't love cats". Our goal is to design learning algorithms that guard against known dataset bias. We formalize the concept of dataset bias under the framework of distribution shift and present a simple debiasing algorithm based on residual fitting, which we call DRiFt. We first learn a biased model that only uses features that are known to relate to dataset bias. Then, we train a debiased model that fits to the residual of the biased model, focusing on examples that cannot be predicted well by biased features only. We use DRiFt to train three high-performing NLI models on two benchmark datasets, SNLI and MNLI. Our debiased models achieve significant gains over baseline models on two challenge test sets, while maintaining reasonable performance on the original test sets.

Method and system for determining interest spaces among online content sources

Abstract: A method and system for determining interest spaces among online content sources. According to one embodiment, a method may include generating a representation of a network of online content sources, where the representation reflects navigation paths and respective navigation path weights among the online content sources, and where the navigation path weights are indicative of user activity among the online content sources. The method may further include generating one or more interest spaces of the network dependent upon the navigation paths and respective navigation path weights, where each interest space includes at least a subset of the online content sources.