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
-
ICML 2021 Workshop on Machine Learning for Data: Automated Creation, Privacy, Bias, ICLR 20222021While recent automatic data augmentation works lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of selecting a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search called Deep AutoAugment (DeepAA).
-
IEEE - The Bulletin of the Technical Committee on Data Engineering2021The customer experience of online shopping is largely contingent on the accuracy of product classification. Considering the amount of products and all the possible categories, it is desirable to construct a framework to auto-assign products into correct categories at scale. Machine learning based systems often suffer from poor data quality, such as incomplete item descriptions, adversarial noise in the
-
IEEE APS/URSI 20212021This paper proposes a simulation methodology to optimize MIMO antenna designs for the system performance parameters. The proposed design flow provides a co-simulation bench to evaluate MIMO antenna designs with system-level criteria. In one example, two MIMO antenna designs are considered, where both of them meet conventional antenna design parameters. The proposed methodology identifies the antenna design
-
ICPP 20212021Low-precision computation, which has been widely supported in contemporary hardware, is considered as one of the most effective methods to accelerate convolutional neural networks. However, low-precision computation is not widely used to speed up Winograd, an algorithm for fast convolution computation, due to the numerical error introduced by combining Winograd transformation and quantization. In this paper
-
Speech Synthesis Workshop2021Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model: highly expressive voices are still challenging even to recent TTS architectures since there seems to be a trade-off between expressiveness in a generated audio and its
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all