Amazon Technologies, Inc.

Sujan Kumar Gonugondla

Sudipta Sengupta

Rama Krishna Sandeep Pokkunuri

Bing Xiang

Ramesh M Nallapati

Parminder Bhatia

Bharathan Balaji

Cameron Dean Whitehouse

Yuchen Tian

Srinivas Iragavarapu

Krzysztof Marcin Walczak

Praphruetpong Athiwaratkun

Jiacheng Guo

Vamshidhar Krishnamurthy Dantu

Karan Aggarwal

Xiaokai Wei

Bohan Yao

Niranjini Rajagopal

Venkatesh Rao

Haifeng Qian

Disclosed implementations determine transient distortions, amplitude distortions, and/or periodic distortions present in a voltage signal measured from an electrical circuit at a location and use those distortions to determine a device type of a device operating on the electrical circuit at the location. In some examples, the voltage signal may be filtered into a plurality of sub-bands and one or more two-dimensional representations generated based on transient distortions, amplitude distortions, and/or periodic distortions determined in each sub-band. The one or more 2D representations may be provided to a deep neural network to determine a device type that generated the distortions on the electrical circuit.

Device type detection

Techniques for using a quantized and/or fused model are described. In some examples, a service is to receive a request to use a trained model, the request including input data; apply a trained model to the input data, the application of the trained model includes fusing one or more matrix multiplication operations with element-wise operations; and output a result from the trained model.

Large language models utilizing element-wise operation-fusion

Growing community of inventors

Secaucus, NJ, United States of America

Sujan Kumar Gonugondla