公开(公告)号：US11699093B2

公开(公告)日：2023-07-11

申请号：US15872547

申请日：2018-01-16

Applicant: Amazon Technologies, Inc.

Inventor： Nagajyothi Nookula ,  Poorna Chand Srinivas Perumalla ,  Aashish Jindia ,  Danjuan Ye ,  Eduardo Manuel Calleja ,  Song Ge ,  Vinay Hanumaiah ,  Wanqiang Chen ,  Safeer Mohiuddin ,  Romi Boimer ,  Madan Mohan Rao Jampani ,  Fei Chen

IPC: G06N5/02 ,  G06N20/00 ,  G06N5/022 ,  G06F9/50

CPC classification number: G06N20/00 ,  G06F9/5044 ,  G06F9/5066 ,  G06N5/022

Abstract: Techniques for generating and executing an execution plan for a machine learning (ML) model using one of an edge device and a non-edge device are described. In some examples, a request for the generation of the execution plan includes at least one objective for the execution of the ML model and the execution plan is generated based at least in part on comparative execution information and network latency information.

公开(公告)号：US12067482B1

公开(公告)日：2024-08-20

申请号：US15888615

申请日：2018-02-05

Applicant: Amazon Technologies, Inc.

Inventor： Poorna Chand Srinivas Perumalla ,  Nagajyothi Nookula ,  Aashish Jindia ,  Vinay Hanumaiah ,  Eduardo Manuel Calleja

IPC: G06F18/25 ,  G06F18/21 ,  G06N3/044 ,  G06N3/08 ,  H04L67/12

CPC classification number: G06N3/08 ,  G06F18/2193 ,  G06F18/251 ,  G06N3/044 ,  H04L67/12

Abstract: Techniques for input adaptation from disparate data sources for heterogeneous machine learning model execution are described. A preprocessing adapter can perform preprocessing of data obtained from edge devices to suit the input data characteristic requirements of one or more machine learning (ML) models. The preprocessing adapter can determine the input data characteristic requirements in a variety of ways, such as via analysis of the input layer of a ML model or through data variation testing and associated feedback resulting from output data generated by the ML model.

公开(公告)号：US11544577B1

公开(公告)日：2023-01-03

申请号：US15881569

申请日：2018-01-26

Applicant: Amazon Technologies, Inc.

Inventor： Nagajyothi Nookula ,  Poorna Chand Srinivas Perumalla ,  Aashish Jindia ,  Eduardo Manuel Calleja ,  Vinay Hanumaiah

IPC: G06N5/02 ,  G06N20/00

Abstract: Techniques for utilizing adaptable filters for edge-based deep learning models are described. Filters may be utilized by an edge electronic device to filter elements of an input data stream so that only a subset of the elements are used as inputs to a machine learning model run by the electronic device, enabling successful operation despite the input data stream potentially being generated at a higher rate than a rate in which the ML model can be executed. The filter can be a differential-type filter that generates difference representations between consecutive elements of the data stream to determine which elements are to be passed on for the ML model, a “smart” filter such as a neural network trained using outputs from the ML model allowing the filter to “learn” which elements are the most likely to be of value to be passed on, or a combination of both.

公开(公告)号：US10810471B1

公开(公告)日：2020-10-20

申请号：US15933152

申请日：2018-03-22

Applicant: Amazon Technologies, Inc.

Inventor： Poorna Chand Srinivas Perumalla ,  Nagajyothi Nookula ,  Eduardo Manuel Calleja ,  Aashish Jindia ,  Vinay Hanumaiah

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/00

Abstract: Techniques for intelligent coalescing of media streams are described. A coalesce engine receives multiple media streams, such as audio or video streams, that are misaligned. The coalesce engine can analyze the media streams by comparing representations of elements of the media streams to detect the misalignment. The coalesce engine may determine an offset amount representing the misalignment, and if the offset amount meets or exceeds a threshold the coalesce engine can work to eliminate the misalignment by introducing one or more artificial delays before sending elements of ones of the media streams that are “ahead” of others of the streams. The coalese engine can additionally or alternatively send feedback to sources of the media streams, causing the source(s) to attempt to mitigate the misalignment.