Customer-obsessed science


-
March 21, 2023Tailoring neighborhood sizes and sampling probability to nodes’ degree of connectivity improves the utility of graph-neural-network embeddings by as much as 230%.
-
March 20, 2023With Alexa Arena, developers can create simulated missions in which humans interact with virtual robots, providing a natural way to build generalizable AI models.
-
March 10, 2023Augmenting query-product graphs with hypergraphs describing product-product relationships improves recall score by more than 48%.
-
-
April 30 - May 4, 2023
-
May 1 - 5, 2023
-
-
March 23, 2023How Amazon is shaping a set of initiatives to enable academia-based talent to harmonize their passions, life stations, and career ambitions.
-
March 15, 2023The submission period opens March 15 and closes on April 26.
-
March 16, 2023SURE provides students from historically underrepresented communities with research experiences at top-tier universities.
-
March 13, 2023Learn how Amazon uses machine-learning techniques to modify different aspects of speech — tone, phrasing, intonation, expressiveness, and accent — to create unique Alexa responses.
-
2023End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore, since they store the entire corpus in their parameters, rare words can be challenging to recall. In this work, we propose augmenting a transducer-based ASR model with
-
2023The deployment of Federated Learning (FL) systems poses various challenges such as data heterogeneity and communication efficiency. We focus on a practical FL setup that has recently drawn attention, where the data distribution on each device is not static but dynamically evolves over time. This setup, referred to as Continual Federated Learning (CFL), suffers from catastrophic forgetting, i.e., the undesired
-
2023This paper describes Distill-Quantize-Tune (DQT), a pipeline to create viable small-footprint multilingual models that can perform NLU directly on extremely resource-constrained Edge devices. We distill semantic knowledge from a large-sized teacher (transformer-based), that has been trained on huge amount of public and private data, into our Edge candidate (student) model (Bi-LSTM based) and further compress
-
2023Human Activity Recognition (HAR) is widely applied on wearable devices in our daily lives. However, acquiring high-quality wearable sensor data set with ground-truths is challenging due to the high cost in collecting data and necessity of domain experts. In order to achieve generalization from limited data, we study augmentation-based Self-Supervised Learning (SSL) for data from wearable devices. However
-
2023In this work, we present Slimmable Neural Networks applied to the problem of small-footprint keyword spotting. We show that slimmable neural networks allow us to create super-nets from Convolutional Neural Networks and Transformers, from which sub-networks of different sizes can be extracted. We demonstrate the usefulness of these models on in-house voice assistant data and Google Speech Commands, and focus
-
March 08, 2023This year’s cohort is researching, among other topics, online changepoint detection algorithms and automated reasoning.
-
March 01, 2023New fellows include PhD candidates in operations research and computer science.
-
February 21, 2023University teams are competing to develop a bot that best responds to customer commands in a virtual world.
Working at Amazon
View allMeet the people driving the innovation essential to being the world’s most customer-centric company.
View all
-
March 14, 2023Ren Zhang and her team tackle the interesting science challenges behind surfacing the most relevant offerings.
-
February 28, 2023How the former astrobiology professor is charting new territory as a scientist for Amazon Flex.
-
February 08, 2023How her background helps her manage a team charged with assisting internal partners to answer questions about the economic impacts of their decisions.