Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
SysML 20182018We argue for the necessity of managing the metadata and lineage of common artifacts in machine learning (ML). We discuss a recently presented lightweight system built for this task, which accelerates users in their ML workflows, and provides a basis for comparability and repeatability of ML experiments. This system tracks the lineage of produced artifacts in ML workloads and automatically extracts metadata
-
SIGMOD 20182018Amazon Aurora is a high-throughput cloud-native relational database offered as part of Amazon Web Services (AWS). One of the more novel differences between Aurora and other relational databases is how it pushes redo processing to a multi-tenant scale-out storage service, purpose-built for Aurora. Doing so reduces networking traffic, avoids checkpoints and crash recovery, enables failovers to replicas without
-
SysML 20182018This paper introduces a brand new tree library treelite. The library is a toolbox to facilitate easy deployment of models and accelerate prediction performance. It has a Python wrapper that allows users to integrate it as part of their workflow. Treelite is able to read tree ensemble models that are trained by any tree libraries, including XGBoost [1], LightGBM [2], and scikit-learn [3]. Treelite is also
-
SLT 20182018Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against background noise, practitioners often perform data augmentation, adding artificially-noised examples to the training set, carrying over the original label. In this paper
-
Interspeech 20182018We propose a simple recurrent model for detecting rare sound events, when the time boundaries of events are available for training. Our model optimizes the combination of an utterancelevel loss, which classifies whether an event occurs in an utterance, and a frame-level loss, which classifies whether each frame corresponds to the event when it does occur. The two losses make use of a shared vectorial representation
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all