Advancing the state of the art

As mobile internet growth continues to bring New Internet Users (NIUs) online, technology has adapted to fit this user segment. User barriers like devices and connectivity have declined as mobile phone prices have become more affordable and infrastructure has continued to develop, connecting more communities globally. App development has also evolved to better suit users on low-cost Android...

We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-...

While additive manufacturing (AM) has facilitated the production of complex structures, it has also highlighted the immense challenge inherent in identifying the optimum AM structure for a given application. Numerical methods are important tools for optimization, but experiment remains the gold standard for studying nonlinear, but critical, mechanical properties such as toughness. To address...

This article discusses principles and best practices for DevOps and SRE practitioners who are deploying and operating ML systems. This article draws on our experiences running production services for the past 15 years as well as from discussions with Google engineers working on diverse ML systems. We will use specific incidents to illustrate where ML-based systems did not behave as expected for...

We introduce TWT; a new treebank for Turkish which consists of web and Wikipedia sentences that are annotated for segmentation, morphology, part-of-speech and dependency relations. To date, it is the largest publicly available human-annotated morpho-syntactic Turkish treebank in terms of the annotated word count. It is also the first large Turkish dependency treebank that has a dedicated...

Thus far, end-to-end (E2E) models have not shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that...

Expensive and time-consuming medical imaging annotation is one of the big challenges for the deep-learning-based computer-aided diagnose (CAD) nodule detection system on the low-dose computed tomography (CT). To address this, we propose a novel active learning approach to improve the training efficiency for a deep-network-based lung nodule detection framework as well as reducing the annotation...